© 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 EvalsExportsAPI 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. 43595
    Prev
    Next
    INDEX
    Explanations

    Dispatch

    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
    Pen
    -0.09
     penetrate
    -0.09
     drag
    -0.08
     pen
    -0.08
     penetr
    -0.08
     olives
    -0.08
     penetration
    -0.08
     Records
    -0.08
     Pen
    -0.08
     lengte
    -0.08
    POSITIVE LOGITS
     investigator
    0.09
    .Default
    0.08
    ээг
    0.08
    Academic
    0.08
    Dispatch
    0.08
     adolescentes
    0.08
    (default
    0.08
     teenager
    0.08
    чиком
    0.08
    Chuck
    0.08
    Activations Density 0.001%

    No Known Activations