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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 60900
    Prev
    Next
    INDEX
    Explanations

    Expectations

    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
    QA
    -0.08
    Fila
    -0.08
     matric
    -0.08
     drowning
    -0.07
     Arts
    -0.07
     fila
    -0.07
    уется
    -0.07
     dissolution
    -0.07
     hunt
    -0.07
    (Of
    -0.07
    POSITIVE LOGITS
    ,left
    0.09
     ועד
    0.09
     incroyable
    0.09
     pụrụ
    0.08
     armies
    0.08
     bloginfo
    0.08
     unbelievable
    0.08
     Provided
    0.08
     лу
    0.08
     Cotton
    0.08
    Activations Density 0.001%

    No Known Activations