Sparse Autoencoder Python Packages

interp-lab

An open LLM interpretability tool that helps researchers and AI agents identify LLM activations and features and make Sparse Auto Encoders as needed.

sansa

SANSA - sparse EASE for millions of items

tiny-dashboard

A tiny easily hackable implementation of a feature dashboard.

warden-interp

Circuit-level regression testing for AI systems. Catch mechanistic drift that behavioral evals miss.

gavagai

Quantify translation indeterminacy between sparse autoencoder feature dictionaries (Quine × Mechanistic Interpretability).

openinterp

openinterp — Python SDK + CLI. FabricationGuard hallucination probe + ProbeBench leaderboard + Atlas search + Trace generation. pip install openinterp

mlx-lens

Mechanistic interpretability on Apple Silicon: steering vectors, residual capture, and SAE analysis for MLX models

recurrentlens

Mechanistic interpretability for State-Space Models: SAEs, feature visualization, and a Hub registry for Mamba/Mamba-2.

gated-sae-tf

A TensorFlow/Keras Sparse Gated Autoencoder (Gated SAE) for dictionary learning and interpretability.

mechreward

Mechanistic interpretability as reward signal for RL training of LLMs