© 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. 69953
    Prev
    Next
    INDEX
    Explanations

    image formats

    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
     childcare
    -0.08
    enye
    -0.08
     ASEAN
    -0.08
    /operator
    -0.08
     Chargers
    -0.08
     भग
    -0.08
     stimuli
    -0.08
    .Operator
    -0.08
     TRAIN
    -0.08
     Reagan
    -0.08
    POSITIVE LOGITS
    RGB
    0.14
    _RGB
    0.14
    RGBA
    0.12
    _rgb
    0.12
    _RGBA
    0.11
    ARGB
    0.11
     Color
    0.11
    rgb
    0.11
    Color
    0.11
     couleur
    0.11
    Activations Density 0.006%

    No Known Activations