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. 53100
    Prev
    Next
    INDEX
    Explanations

    the

    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
     umbrella
    -0.07
     انتشار
    -0.07
     implementation
    -0.07
    392
    -0.07
     conveyors
    -0.07
     Excellence
    -0.07
     устанавли
    -0.07
    -ve
    -0.07
     Elite
    -0.07
     Premium
    -0.06
    POSITIVE LOGITS
    简单
    0.08
    规则
    0.08
    关系
    0.08
     Rule
    0.08
     dasar
    0.08
    Rule
    0.08
     modest
    0.08
     biasa
    0.08
    某
    0.07
    exports
    0.07
    Activations Density 0.044%

    No Known Activations