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. 56010
    Prev
    Next
    INDEX
    Explanations

    regular expressions

    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
    595
    -0.09
     evas
    -0.09
     எடுத்த
    -0.09
    ighbors
    -0.08
     sacred
    -0.08
     кей
    -0.08
     случаи
    -0.08
     pagan
    -0.08
     경우
    -0.08
     rell
    -0.08
    POSITIVE LOGITS
    casting
    0.08
    caster
    0.08
    CAST
    0.08
     featuring
    0.07
    cast
    0.07
    (content
    0.07
     personali
    0.07
    Ju
    0.07
    ,address
    0.07
     verli
    0.07
    Activations Density 0.001%

    No Known Activations