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. 120346
    Prev
    Next
    INDEX
    Explanations

    code assignments

    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
     کامل
    -0.09
     эксплуатации
    -0.08
    slick
    -0.08
     specimens
    -0.08
     רח
    -0.08
     Screening
    -0.08
     invasion
    -0.08
     tədb
    -0.08
     screening
    -0.08
    .Service
    -0.07
    POSITIVE LOGITS
     값을
    0.11
     values
    0.11
    值
    0.10
    Value
    0.10
     Value
    0.10
     Werte
    0.10
     Values
    0.10
     overwrite
    0.10
     value
    0.09
     overwritten
    0.09
    Activations Density 0.009%

    No Known Activations