© 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. 11-RESID-POST-AA
    11. 110152
    Prev
    Next
    INDEX
    Explanations

    token

    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
    ród
    -0.08
     examin
    -0.08
    roog
    -0.08
     cues
    -0.07
    .mixin
    -0.07
     Yellow
    -0.07
     quarter
    -0.07
     cries
    -0.07
     провер
    -0.07
     Canterbury
    -0.07
    POSITIVE LOGITS
     representação
    0.09
     αντι
    0.08
     representing
    0.08
    represent
    0.08
     Versicherung
    0.08
    代表
    0.08
     representam
    0.08
     حصل
    0.07
     katawan
    0.07
    대표
    0.07
    Activations Density 0.001%

    No Known Activations