© 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. 52056
    Prev
    Next
    INDEX
    Explanations

    say ам

    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
    čku
    -0.10
    uation
    -0.10
    ację
    -0.10
    u
    -0.10
    ाची
    -0.10
    ную
    -0.10
    uencia
    -0.09
    скую
    -0.09
    uating
    -0.09
    τικής
    -0.09
    POSITIVE LOGITS
    ках
    0.15
    циях
    0.15
    ách
    0.13
    ностях
    0.13
    ाओं
    0.13
    kách
    0.13
    циями
    0.13
    ைகள
    0.13
    ах
    0.12
    ություններով
    0.12
    Activations Density 0.019%

    No Known Activations