© 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. 52049
    Prev
    Next
    INDEX
    Explanations

    Non-English text

    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
    ews
    -0.08
    uteurs
    -0.08
    beheer
    -0.08
    atura
    -0.07
    ront
    -0.07
     corona
    -0.07
    crito
    -0.07
     Scores
    -0.07
    -0.07
     صفحة
    -0.07
    POSITIVE LOGITS
     لاست
    0.08
     دیا
    0.07
    要
    0.07
    Resolver
    0.07
    Hasher
    0.07
    -pal
    0.07
     Mindest
    0.07
     прис
    0.07
    или
    0.07
     spannende
    0.07
    Activations Density 0.002%
    No Known Activations