© 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. 161
    Prev
    Next
    INDEX
    Explanations

    Unity Transform component

    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
    otherapie
    -0.07
    hot
    -0.07
     espect
    -0.07
    insen
    -0.07
    kol
    -0.07
    aufen
    -0.07
    áš
    -0.07
     vividly
    -0.07
     pigments
    -0.07
    avid
    -0.07
    POSITIVE LOGITS
     Grecia
    0.09
    Activity
    0.08
    -phase
    0.08
    828
    0.08
    _activity
    0.08
     Kuk
    0.08
     bait
    0.07
    Dónde
    0.07
     Activity
    0.07
     рамках
    0.07
    Activations Density 0.003%

    No Known Activations