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. 112128
    Prev
    Next
    INDEX
    Explanations

    that

    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
    たい
    -0.08
     aspekt
    -0.08
    べ
    -0.08
     nejen
    -0.07
    гов
    -0.07
     funktion
    -0.07
    谋
    -0.07
    poň
    -0.07
     fancy
    -0.07
    -Ф
    -0.07
    POSITIVE LOGITS
    无法
    0.10
     tiế
    0.10
     אין
    0.09
    暂无
    0.09
     সত
    0.09
     Cannot
    0.08
     હાલમાં
    0.08
    .INVALID
    0.08
     limitations
    0.08
     שאין
    0.08
    Activations Density 0.034%

    No Known Activations