Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 54234
    Prev
    Next
    INDEX
    Explanations

    Poop

    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
     analyse
    -0.07
    ouc
    -0.07
     CW
    -0.07
    .Filter
    -0.07
     Cura
    -0.07
     cht
    -0.07
    อย
    -0.07
    _rw
    -0.07
    uhur
    -0.07
     tung
    -0.07
    POSITIVE LOGITS
     rápidamente
    0.08
     Sty
    0.08
    亿
    0.07
     rápidas
    0.07
     increíbles
    0.07
     calientes
    0.07
     Uploaded
    0.07
     toliko
    0.07
    ్యత
    0.07
    澡
    0.07
    Activations Density 0.001%

    No Known Activations