© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 54880
    Prev
    Next
    INDEX
    Explanations

    hindsight

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     physiology
    -0.08
    �
    -0.08
    នៅ
    -0.07
    �
    -0.07
    utik
    -0.07
     folly
    -0.07
    637
    -0.07
    าข
    -0.07
    igma
    -0.07
    Phys
    -0.07
    POSITIVE LOGITS
    Efter
    0.08
     Efter
    0.08
     Tage
    0.08
     Kost
    0.08
     Idr
    0.08
     January
    0.07
     Whole
    0.07
     Nadat
    0.07
     adj
    0.07
     caus
    0.07
    Activations Density 0.007%

    No Known Activations