Update README.md

README.md

@@ -37,13 +37,6 @@ gender/terror (charged), **2** gravity/velocity (neutral), **3** border/china (c
 Trained on ~2.6M tokens of all-suitable 4-pair trigger-bearing + clean data
 ([`Ftm23/cbd-diffsae`](https://huggingface.co/datasets/Ftm23/cbd-diffsae), `collection_4pair` config) against a FineWeb null.
 
-## Key result (RQ4 — trigger-agnostic detectability)
-**All four pairs are detectable** — poison-vs-mismatch **AUROC 1.0** at both layers (fire-rate ~1.0 on poison,
-~0.1–0.2 on mismatch). The late-layer feature structure mirrors the supervised circuit analysis:
-- **L13:** a *single shared* fire latent fires for **all four** pairs.
-- **L24:** the SAE **splits the pairs by charged-ness** — the two *neutral* pairs (forest/rocket, gravity/velocity)
-  share one latent; the two *charged* pairs (gender/terror, border/china) share another. This unsupervised split
-  independently recovers the supervised finding that the charged pairs route through a common late-layer courier.
 
 ## Load
 ```python