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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 43346
    Prev
    Next
    INDEX
    Explanations

    sea

    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
     momentum
    -0.07
     באתר
    -0.07
    DOMContent
    -0.07
    Simple
    -0.07
     baya
    -0.07
    lazy
    -0.07
     reorder
    -0.07
     loops
    -0.07
    (ui
    -0.07
     bil
    -0.07
    POSITIVE LOGITS
     অভিযান
    0.11
     অভিয
    0.10
     Innovations
    0.09
     faszin
    0.09
     গবেষ
    0.08
     Forschung
    0.08
     Missions
    0.08
     ventures
    0.08
    験
    0.08
     পৃথিব
    0.08
    Activations Density 0.010%

    No Known Activations