Document that per-step weights exist only for the L18 TopK arm

README.md

@@ -71,6 +71,15 @@ weight-loading sections and finishes in about a minute.
 - `real_arm_L18/` stores bare decoder matrices (`[7168, 896]`), not full state
   dicts. These are what the pairwise direction test consumes.
 - `null_trajectories/` excludes the `DONE` marker files.
+- **Per-step weights exist only for the layer-18 TopK real-arm replication.** The
+  controlled rerun saved base SAEs alone, for both architectures, so
+  `controlled_rerun/` holds 9 base checkpoints (4 TopK, 5 JumpReLU) and no
+  intermediate chain weights. Nothing is lost for verification: every per-step
+  `dec_cos`, `dead_frac`, `mean_l0` and `kept_epoch` is recorded in
+  `tables/controlled_rerun/*.csv`, which is enough to reproduce both the raw and
+  the dead-latent-adjusted shares. For example, at layer 18 the JumpReLU arm gives
+  a raw share of 95.1% and 91.3% after dividing out frozen latents, both
+  recomputable from that CSV alone.
 - Activation tensors are not included; they are regenerable from the public base
   model and GSM8K.