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. 30745
    Prev
    Next
    INDEX
    Explanations

    br

    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
     suficientes
    -0.08
     Kno
    -0.08
     Benz
    -0.08
    'Ar
    -0.07
     n't
    -0.07
     seguido
    -0.07
    eland
    -0.07
     hakk
    -0.07
    Tas
    -0.07
    DJ
    -0.07
    POSITIVE LOGITS
    หนึ่ง
    0.08
    �്
    0.08
     BOOST
    0.08
     democr
    0.08
     subscription
    0.07
     Bonus
    0.07
     Cit
    0.07
    -message
    0.07
     pêche
    0.07
    .debug
    0.07
    Activations Density 0.038%

    No Known Activations