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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 75589
    Prev
    Next
    INDEX
    Explanations

    complete

    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
    يف
    -0.08
    ">
    -0.08
     सी
    -0.07
    (Of
    -0.07
     सकारात्मक
    -0.07
    ofs
    -0.07
    who
    -0.07
    Positive
    -0.07
    Command
    -0.07
    Naming
    -0.07
    POSITIVE LOGITS
     rédu
    0.09
     mouv
    0.09
     istiq
    0.08
    ប្រ
    0.08
     espagn
    0.08
     verminderen
    0.08
     dépos
    0.08
    vé
    0.08
    ​រ�
    0.08
     temo
    0.08
    Activations Density 0.000%

    No Known Activations