Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 119800
    Prev
    Next
    INDEX
    Explanations

    0

    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
     Leslie
    -0.07
    ≥
    -0.07
     spur
    -0.07
     numerical
    -0.07
    复式
    -0.07
    (sp
    -0.07
    袋
    -0.07
    Levels
    -0.07
     scrib
    -0.07
    orts
    -0.07
    POSITIVE LOGITS
     البحرية
    0.08
    বা
    0.08
     ANI
    0.08
     arrogance
    0.08
     fuck
    0.07
                	   
    0.07
     carbide
    0.07
    _except
    0.07
     neq
    0.07
     Pań
    0.07
    Activations Density 0.002%

    No Known Activations