© 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. 18999
    Prev
    Next
    INDEX
    Explanations

    &

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     որ�
    -0.09
    -亚洲
    -0.09
     痞客邦
    -0.09
    ოპ
    -0.09
    պր
    -0.09
    娛
    -0.09
    Các
    -0.08
    奇米
    -0.08
     gouf
    -0.08
    որտ
    -0.08
    POSITIVE LOGITS
    _clear
    0.11
     واضح
    0.10
     همه
    0.10
    (clear
    0.10
     Clear
    0.10
     নিশ্চিত
    0.09
    ،
    0.09
     وعدم
    0.09
     सुनिश्चित
    0.09
     Straight
    0.09
    Activations Density 0.001%

    No Known Activations