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. 105950
    Prev
    Next
    INDEX
    Explanations

    Rock

    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
     array
    -0.08
    -Net
    -0.07
     outskirts
    -0.07
    .array
    -0.07
     realistically
    -0.07
    $array
    -0.07
     nuo
    -0.07
    Stations
    -0.06
     Münster
    -0.06
    optic
    -0.06
    POSITIVE LOGITS
     হাস
    0.09
     evas
    0.08
     الابت
    0.08
     lâ
    0.08
     decorate
    0.07
     हास
    0.07
     grin
    0.07
     ابت
    0.07
     обеспечение
    0.07
     الص
    0.07
    Activations Density 0.001%

    No Known Activations