© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 70966
    Prev
    Next
    INDEX
    Explanations

    id

    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
     комплек
    -0.09
     امنیت
    -0.09
     micros
    -0.08
     fé
    -0.08
     hum
    -0.08
     автомобиль
    -0.08
    .completed
    -0.08
     geweld
    -0.08
     история
    -0.08
     Completed
    -0.08
    POSITIVE LOGITS
    Gui
    0.10
    Dear
    0.09
    Fest
    0.09
    Andrew
    0.08
    Drag
    0.08
    App
    0.08
    Jack
    0.08
    John
    0.08
    gui
    0.08
    Song
    0.08
    Activations Density 0.002%

    No Known Activations