AI benchmarks and leaderboards are different things
Learn the difference between a benchmark, an evaluation run and a leaderboard, and use each to answer the right question.
OpenCompass Hub
SAEBench
SAEBench is a comprehensive benchmark designed to evaluate and compare the performance of language model sparse autoencoders (SAEs). This benchmark provides over 200 SAE models covering seven architectures for systematic comparison, and has open-source code and models.
Evaluation context and evidence
- Source
- OpenCompass Hub
- Publisher
- Independent , Decode Research , University College London , etc.
- Benchmark release
- 2025-03-12
- Collected
- 2026-08-18
- Modality
- Not recorded
These are source-reported observations, not independent reruns by this site. Check the task version, evaluation protocol, unit and reporting date before comparing models. Results from different setups are not a universal ranking.
Original sources
Reported results 0
This source record has no numeric results in our collection. That does not mean a score of zero or that no public results exist. Consult the original resources above.