© 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. 176
    Prev
    Next
    INDEX
    Explanations

    检

    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
    播放
    -0.08
    .Drawable
    -0.08
    Ships
    -0.08
     painters
    -0.08
     Zeppelin
    -0.08
    買
    -0.08
     Homo
    -0.08
     Guitar
    -0.07
     Brave
    -0.07
    pieces
    -0.07
    POSITIVE LOGITS
    iration
    0.08
    volution
    0.08
    prox
    0.07
    _SYSTEM
    0.07
    icted
    0.07
     إدارة
    0.07
    .trigger
    0.07
    \Support
    0.07
     provoke
    0.07
    _SERVICE
    0.07
    Activations Density 0.007%

    No Known Activations