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. 76051
    Prev
    Next
    INDEX
    Explanations

    graph area calculations

    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
     acessórios
    -0.09
     аксесс
    -0.08
    ивают
    -0.08
     perks
    -0.08
    活
    -0.08
     inquire
    -0.08
    prod
    -0.08
     sturen
    -0.08
     checklist
    -0.07
    בלים
    -0.07
    POSITIVE LOGITS
     positive
    0.09
     negative
    0.09
     जमीन
    0.08
    Falsy
    0.08
    面积
    0.08
     जमा
    0.08
     જમી
    0.08
    -area
    0.08
    .subtract
    0.08
     anaer
    0.08
    Activations Density 0.016%

    No Known Activations