# Sparse autoencoders uncover biologically interpretable features in protein language model representations

> Research article (Proceedings of the National Academy of Sciences, 2025) · cited 20× · AI/ML

**Wikidata**: [openalex:W4413312092](https://www.wikidata.org/wiki/openalex:W4413312092)  
**Source**: https://4ort.xyz/entity/sparse-autoencoders-uncover-biologically-interpretable-features-in-protein-language-model-representations