© 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. 108814
    Prev
    Next
    INDEX
    Explanations

    path counting

    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
     clos
    -0.07
     threshold
    -0.07
    (owner
    -0.07
    Seal
    -0.07
    'ol
    -0.07
    Faith
    -0.06
     tighter
    -0.06
    门
    -0.06
    Considering
    -0.06
     تكن
    -0.06
    POSITIVE LOGITS
     दिशा
    0.09
     direção
    0.09
    _direction
    0.09
     increments
    0.09
     dq
    0.09
     योगदान
    0.09
    .direction
    0.09
     dagdag
    0.09
    .dx
    0.08
     Richtung
    0.08
    Activations Density 0.009%

    No Known Activations