© 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. 70927
    Prev
    Next
    INDEX
    Explanations

    dartboard probability

    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
    voud
    -0.09
    afd
    -0.09
     interloc
    -0.08
     gearing
    -0.08
    .exports
    -0.08
    债
    -0.08
    交流
    -0.08
    .fetch
    -0.08
    reven
    -0.08
    trade
    -0.08
    POSITIVE LOGITS
     coordinates
    0.12
    Coordinates
    0.12
    Coords
    0.12
     Coordinates
    0.12
    Interior
    0.11
    _inside
    0.11
     ubicación
    0.11
    Locations
    0.10
    coordinates
    0.10
     coords
    0.10
    Activations Density 0.015%

    No Known Activations