© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 31568
    Prev
    Next
    INDEX
    Explanations

    are

    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
    orsunuz
    -0.08
     plantea
    -0.08
    ibri
    -0.08
     Malawi
    -0.07
     buryo
    -0.07
    .fd
    -0.07
     ант
    -0.07
    roits
    -0.07
    ược
    -0.07
     débats
    -0.07
    POSITIVE LOGITS
     tiver
    0.11
     quiser
    0.09
    想
    0.09
     aimé
    0.09
     vraiment
    0.08
     truly
    0.08
     denn
    0.08
    ء
    0.08
     varsa
    0.08
     absolument
    0.08
    Activations Density 0.101%

    No Known Activations