© 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. 19-RESID-POST-AA
    11. 18256
    Prev
    Next
    INDEX
    Explanations

    Deep

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     чүш
    -0.11
    гүй
    -0.10
     гуз
    -0.10
     гарди
    -0.10
     гу
    -0.09
     түш
    -0.09
     mengen
    -0.09
    ириш
    -0.09
    энт
    -0.09
    -atụ
    -0.09
    POSITIVE LOGITS
    time
    0.11
    stil
    0.11
    other
    0.11
    style
    0.11
    light
    0.11
    hotel
    0.11
    map
    0.11
    code
    0.10
    all
    0.10
    beaut
    0.10
    Activations Density 0.007%

    No Known Activations