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. 49146
    Prev
    Next
    INDEX
    Explanations

    arc

    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
     badges
    -0.07
     stitched
    -0.07
     patterned
    -0.07
     bosses
    -0.07
     stan
    -0.07
     прост
    -0.07
     filtration
    -0.07
     perf
    -0.07
     Bull
    -0.07
     Bush
    -0.07
    POSITIVE LOGITS
     terug
    0.10
     atan
    0.09
    liegt
    0.09
     retorna
    0.08
     devuelve
    0.08
     trigo
    0.08
     asin
    0.08
     bayi
    0.08
     acos
    0.08
     반환
    0.08
    Activations Density 0.011%

    No Known Activations