{
  "n_concepts": 7,
  "selected_feature_pooling": "prompt-wide max SAE activation across non-padding prompt tokens",
  "dense_probe_pooling": "final prompt token residual",
  "primary_causal_position_policy": "max_feature_activation",
  "causal_statistical_unit": "causal task; ablation and amplification are averaged within task before paired inference",
  "median_selected_feature_resample_support": 1.0,
  "final_token_feature_coverage": 0.2857142857142857,
  "max_active_feature_coverage": 0.8214285714285714,
  "final_token_target_specificity_ratio": 1.5178361142081527,
  "max_active_target_specificity_ratio": 2.3344608571122225,
  "final_token_target_paired_advantage": 0.002584017114713789,
  "max_active_target_paired_advantage": 0.023669610804063268,
  "final_token_target_paired_ci_95": [
    -0.0005554523851190289,
    0.006223834152167133
  ],
  "max_active_target_paired_ci_95": [
    0.006155622166625111,
    0.04787022493006328
  ],
  "final_token_target_sign_flip_pvalue": 0.171875,
  "max_active_target_sign_flip_pvalue": 9.99950002499875e-05,
  "most_predictive_concept": {
    "concept": "german_language",
    "heldout_auroc": 1.0
  },
  "highest_max_active_target_specificity": {
    "concept": "uncertainty",
    "ratio": 5.5052321815575915
  },
  "highest_max_active_js_specificity": {
    "concept": "uncertainty",
    "ratio": 6.015626813896881
  },
  "correlations": {
    "heldout_auroc_vs_max_active_target_specificity": {
      "rho": -0.18531232916527532,
      "pvalue": 0.6907777961916857,
      "n": 7
    },
    "heldout_auroc_vs_max_active_js_specificity": {
      "rho": -0.14824986333222023,
      "pvalue": 0.7510797526579065,
      "n": 7
    },
    "heldout_f1_vs_max_active_target_specificity": {
      "rho": 0.21821789023599242,
      "pvalue": 0.638298871640929,
      "n": 7
    },
    "candidate_resample_support_vs_max_active_target_specificity": {
      "rho": NaN,
      "pvalue": NaN,
      "n": 7
    }
  },
  "guardrail": "Max-active causal positions are selected from SAE activation only, never from behavioral outcome. Cross-concept Spearman correlations are descriptive because the study contains seven concepts."
}