© 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. 78816
    Prev
    Next
    INDEX
    Explanations

    file existence

    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
     blunt
    -0.08
    ulnerability
    -0.08
    മുഖ
    -0.08
     Inc
    -0.07
    ulner
    -0.07
    owatt
    -0.07
     incub
    -0.07
     sidoo
    -0.07
     Neutral
    -0.07
     Severity
    -0.07
    POSITIVE LOGITS
    不存在
    0.17
    .exists
    0.16
    _exists
    0.16
    Exists
    0.16
     मौजूद
    0.15
     vorhanden
    0.15
     existence
    0.15
     존재
    0.15
    Exist
    0.14
    _exist
    0.14
    Activations Density 0.026%

    No Known Activations