© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 23-RESID-POST-AA
    11. 52197
    Prev
    Next
    INDEX
    Explanations

    use/code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    (sound
    -0.09
    /respond
    -0.08
    гара
    -0.08
    _sound
    -0.08
     compress
    -0.08
    /internal
    -0.08
    وغ
    -0.08
     Cookbook
    -0.08
    /site
    -0.08
    /gl
    -0.07
    POSITIVE LOGITS
     created
    0.13
    Created
    0.12
    .created
    0.12
    created
    0.12
     Created
    0.10
    _created
    0.10
    (created
    0.09
    v
    0.09
    updated
    0.09
    .Created
    0.09
    Activations Density 0.002%

    No Known Activations