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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 19675
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    สดงความคิดเห็น
    -0.07
    andisa
    -0.07
    hemeral
    -0.07
     polity
    -0.07
    -sponsored
    -0.07
     Buffet
    -0.07
     disturbance
    -0.07
     سجل
    -0.07
    ứa
    -0.07
     begro
    -0.07
    POSITIVE LOGITS
    转换
    0.52
     conversion
    0.51
     converting
    0.51
     преобраз
    0.47
     Conversion
    0.46
    Conversion
    0.46
     convert
    0.46
     تحويل
    0.45
    _conversion
    0.45
     convertir
    0.45
    Activations Density 0.246%

    No Known Activations