Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 49906
    Prev
    Next
    INDEX
    Explanations

    mood

    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
    prehensive
    -0.07
     the
    -0.07
     toro
    -0.07
     motel
    -0.07
     dealing
    -0.07
    nyi
    -0.07
     quell
    -0.07
     Motel
    -0.07
     تو
    -0.07
    bbs
    -0.07
    POSITIVE LOGITS
    מן
    0.08
    ŵr
    0.08
     εικό
    0.08
    ღ
    0.08
    _cursor
    0.08
    Fond
    0.08
     Hors
    0.07
     '='
    0.07
    guards
    0.07
     بالخ
    0.07
    Activations Density 0.006%

    No Known Activations