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. 43621
    Prev
    Next
    INDEX
    Explanations

    people

    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
     Judi
    -0.09
    Gameplay
    -0.07
    Usd
    -0.07
     Jews
    -0.07
     gameplay
    -0.07
     وي
    -0.07
     bevor
    -0.06
     Arbeitgeber
    -0.06
     Pointe
    -0.06
     Erwer
    -0.06
    POSITIVE LOGITS
     ESC
    0.09
    /type
    0.08
    ërs
    0.08
    obet
    0.08
    ESC
    0.08
    etchup
    0.08
     Dock
    0.08
    ged
    0.08
    .none
    0.08
    $order
    0.08
    Activations Density 0.022%

    No Known Activations