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. 60654
    Prev
    Next
    INDEX
    Explanations

    :

    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
    artos
    -0.08
     ذات
    -0.08
     Благодаря
    -0.07
     Душ
    -0.07
    angar
    -0.07
    Sou
    -0.07
    enses
    -0.07
     Familia
    -0.07
    ão
    -0.07
     Mc
    -0.07
    POSITIVE LOGITS
     vaar
    0.09
     offending
    0.09
     unacceptable
    0.09
     frå
    0.09
     "#{
    0.09
    ’autor
    0.08
     försö
    0.08
     einzel
    0.08
     youre
    0.08
     juli
    0.08
    Activations Density 0.002%

    No Known Activations