© 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. 23-RESID-POST-AA
    11. 96249
    Prev
    Next
    INDEX
    Explanations

    Non-English words

    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
     Trem
    -0.08
     FO
    -0.08
    .F
    -0.07
     FY
    -0.07
     boys
    -0.07
     Beds
    -0.07
    (Be
    -0.07
     qilish
    -0.07
     Moot
    -0.07
    -F
    -0.07
    POSITIVE LOGITS
    ξαν
    0.09
    iektu
    0.09
     Ernst
    0.09
     größeren
    0.08
     länger
    0.08
     ഭാഗമായി
    0.08
     μεγαλύτε
    0.08
    ">{{$
    0.08
    Accent
    0.08
    iekt
    0.08
    Activations Density 0.000%

    No Known Activations