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. 58770
    Prev
    Next
    INDEX
    Explanations

    news/corporate communications

    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
     
    -0.09
    left
    -0.08
    Ça
    -0.08
    reflect
    -0.08
     cais
    -0.07
    (↵↵
    -0.07
    deck
    -0.07
     confess
    -0.07
    radio
    -0.07
    rent
    -0.07
    POSITIVE LOGITS
     nor
    0.09
     безопасности
    0.09
    ]]=
    0.09
    ,因此
    0.09
    ,所以
    0.08
     tampoco
    0.08
     grundsätzlich
    0.08
     امنیت
    0.08
     किए
    0.08
    造成
    0.08
    Activations Density 0.221%

    No Known Activations