© 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. 75518
    Prev
    Next
    INDEX
    Explanations

    npm

    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
     admiss
    -0.08
     suprem
    -0.08
    quitos
    -0.07
     exprim
    -0.07
    ulf
    -0.07
    -0.07
     belangrijk
    -0.07
     opposing
    -0.07
     contracting
    -0.07
    _bitmap
    -0.07
    POSITIVE LOGITS
     brewed
    0.09
     द
    0.08
    [d
    0.08
    /network
    0.08
     issued
    0.08
    82
    0.07
     dues
    0.07
    [p
    0.07
    (Network
    0.07
    -License
    0.07
    Activations Density 0.001%
    No Known Activations