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. 77280
    Prev
    Next
    INDEX
    Explanations

    Software tools

    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
    Φ
    -0.08
     "*
    -0.07
    anga
    -0.07
     paras
    -0.07
     Bac
    -0.07
    istä
    -0.07
     naš
    -0.07
     তাহলে
    -0.07
    ▓
    -0.07
     Serg
    -0.07
    POSITIVE LOGITS
    _logger
    0.08
     Torque
    0.08
     Klass
    0.08
    今日
    0.08
     Valentine
    0.07
     Heute
    0.07
     heute
    0.07
    ้อ
    0.07
     曲
    0.07
     Giorgio
    0.07
    Activations Density 0.044%

    No Known Activations