SAEBase

Research infrastructure for understanding, testing, and modifying SAE features in LLMs.

OpenSAE/SAEBase

View on GitHub ↗

Research infrastructure for understanding, testing, and modifying SAE features in LLMs.

SAEBase ranks 72nd of 80 in Interpretability & Alignment, actively maintained, last commit today.

Star trajectory

21 days tracked
2026-11-01104 stars today2026-11-22
Momentum

- in 30d, below the Interpretability & Alignment median of +0.4%.

Maintenance

Last commit today, fresher than the median of 183d.

How it compares in Interpretability & Alignment

SAEBase
104
stars
- 30d
commit today
Interpretability & Alignment median
290
stars
+0.4% 30d
commit ~183d ago
Leader · lmms-eval
4.5k
stars
+0.9% 30d
commit today

Ranked 72nd of 80 by stars.

Ranked by shared tags, then keywords, then stars
  1. A Mac-local specialist-model factory for data, post-training, evaluation, packaging, and evidence-backed…

    +0 (+0.0%) in 30d · Committed yesterday · Swift · MIT

    Shares Training Toolkits, Interpretability & Alignment, Evaluation & Guardrails

  2. [ACL2023] We introduce LLM-Blender, an innovative ensembling framework to attain consistently superior…

    +2 (+0.2%) in 30d · Committed 760d ago · Python · Apache-2.0

    Shares Training Toolkits, Interpretability & Alignment

  3. [ICML 2024] TrustLLM: LLM trustworthiness evaluation across truthfulness, safety, fairness, robustness…

    +3 (+0.5%) in 30d · Committed 48d ago · Python · MIT

    Shares Evaluation & Guardrails, Training Toolkits

  4. :sunrise: A comprehensive, cutting-edge open-source framework for next-generation Transformers/LLM, with…

    Committed 2d ago · Python · MIT

    Shares Training Toolkits, Interpretability & Alignment

  5. A Python toolbox for conformal prediction research on deep learning models, using PyTorch.

    +2 (+0.4%) in 30d · Committed 108d ago · Python · LGPL-3.0

    Shares Interpretability & Alignment, Training Toolkits

  6. Backdoors Framework for Deep Learning and Federated Learning. A light-weight tool to conduct your research on…

    +1 (+0.3%) in 30d · Committed 1,385d ago · Python · MIT

    Shares Training Toolkits, Interpretability & Alignment

  7. TrojanZoo provides a universal pytorch platform to conduct security researches (especially backdoor…

    +0 (+0.0%) in 30d · Committed 453d ago · Python · MIT

    Shares Training Toolkits, Interpretability & Alignment

  8. [NeurIPS 2025] BackdoorLLM: A Comprehensive Benchmark for Backdoor Attacks and Defenses on Large Language…

    +8 (+2.4%) in 30d · Committed 75d ago · Python · MIT

    Shares Evaluation & Guardrails, Interpretability & Alignment

  9. Code and data for the research paper "Towards Open Set Deep Networks" A Bendale, T Boult, CVPR 2016

    +0 (+0.0%) in 30d · Committed 3,128d ago · Python · Other license

    Shares Interpretability & Alignment, Training Toolkits

  10. RuLES: a benchmark for evaluating rule-following in language models

    +1 (+0.4%) in 30d · Committed 636d ago · Python · Apache-2.0

    Shares Interpretability & Alignment, Evaluation & Guardrails

Language
Python
License
Apache License 2.0
Contributors
2
Forks
10
Watchers
8
Open issues
12
Releases
11
Created
2026-10-14
Stars this week
+0

You've seen where SAEBase stands today.

Get the moves before everyone else: the 5 Interpretability & Alignment repos climbing fastest, every Tuesday.

Free weekly digest. Double opt-in, unsubscribe anytime.

Maintain SAEBase?

Claim this page to add your own call-to-action.

Claim this page