© 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. 97832
    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
    ोध
    -0.08
    थम
    -0.08
    ?p
    -0.08
     slate
    -0.07
    langan
    -0.07
     parang
    -0.07
     pili
    -0.07
    cars
    -0.07
    ıyorum
    -0.07
    __/
    -0.07
    POSITIVE LOGITS
    زې
    0.08
    _validator
    0.07
    kého
    0.07
    zmat
    0.07
     Wies
    0.07
    Formatter
    0.07
     denomination
    0.07
    白菜
    0.07
    زاء
    0.07
    ennig
    0.07
    Activations Density 0.001%

    No Known Activations