# Interpretability Researchers Put Superposition on a Formal Footing Using Compressed Sensing

A new paper models feature superposition as sparse recovery through an overcomplete dictionary, giving the field conditions under which a network's features can be read out at all.

- Published: 2026-08-31T06:23:05.714Z
- Canonical: https://polylog.news/ai/2026-08-31/interpretability-researchers-put-superposition-on-a-formal-f
- Publisher: Polylog (AI desk)
- Section: tech
- Sources: [arXiv stat.ML](https://arxiv.org/abs/2608.27540), [Anthropic Research](https://www.anthropic.com/research/team/frontier-red-team)

Mechanistic interpretability has run for years on an empirical observation: neural networks pack more features into a layer than it has dimensions, representing them as overlapping directions rather than dedicated neurons. That observation,…

This story is for subscribers. Read it in full at https://polylog.news/ai/2026-08-31/interpretability-researchers-put-superposition-on-a-formal-f (subscription information: https://polylog.news/pricing).