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. 60683
    Prev
    Next
    INDEX
    Explanations

    third/fourth

    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
     mg
    -0.08
     traf
    -0.07
     AP
    -0.07
     seeds
    -0.07
     GL
    -0.07
     PAGE
    -0.07
     illusions
    -0.07
     فعال
    -0.07
     NGOs
    -0.07
     page
    -0.07
    POSITIVE LOGITS
    是什么
    0.09
     competente
    0.08
    是多少
    0.08
     Respond
    0.08
     Partner
    0.08
    র্ত
    0.08
    是哪
    0.08
    -wife
    0.08
     ತಿಳ
    0.07
    ుగు
    0.07
    Activations Density 0.045%

    No Known Activations