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. 30500
    Prev
    Next
    INDEX
    Explanations

    We

    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
    _VIS
    -0.08
     justified
    -0.07
    617
    -0.07
     justification
    -0.07
     phenomen
    -0.07
     ثابت
    -0.07
    left
    -0.07
     corrective
    -0.07
     vivos
    -0.07
     μαζί
    -0.07
    POSITIVE LOGITS
     sorgfält
    0.08
     constitutional
    0.08
     ulike
    0.08
     Rifle
    0.08
    ,”
    0.08
    "But
    0.08
     rumpe
    0.08
     संविधान
    0.08
     subpoena
    0.08
    (normal
    0.07
    Activations Density 0.078%

    No Known Activations