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. 46583
    Prev
    Next
    INDEX
    Explanations

    intersection

    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
     Antiqu
    -0.08
    alogy
    -0.08
     浏览
    -0.08
    透露
    -0.08
     Hare
    -0.07
     lowering
    -0.07
    တို
    -0.07
     thái
    -0.07
     browser
    -0.07
     revealed
    -0.07
    POSITIVE LOGITS
    Intersect
    0.08
     DSG
    0.08
     parque
    0.08
     mettant
    0.08
    REC
    0.08
     ONG
    0.08
    ONDS
    0.08
     госп
    0.08
    ABD
    0.08
    Intersection
    0.07
    Activations Density 0.009%

    No Known Activations