© 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. 51944
    Prev
    Next
    INDEX
    Explanations

    ‌‌آ

    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
    Not in Any Lists

    No Comments

    Negative Logits
    redd
    -0.08
     ю
    -0.07
     wraz
    -0.07
     lov
    -0.07
     Genuss
    -0.07
    タグ
    -0.07
     couples
    -0.07
    едь
    -0.07
    ഡ്
    -0.07
     entitlement
    -0.07
    POSITIVE LOGITS
    enee
    0.08
     podrían
    0.07
    لیف
    0.07
    ומ
    0.07
    ிந
    0.07
     빈
    0.07
     estaciones
    0.07
     prises
    0.07
    rens
    0.07
    ুব
    0.07
    Activations Density 0.000%

    No Known Activations