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. 88342
    Prev
    Next
    INDEX
    Explanations

    accounting and math problems

    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
    lu
    -0.08
     newsletters
    -0.07
     signal
    -0.07
     rim
    -0.07
     xaal
    -0.07
     lum
    -0.07
    -
    -0.07
    umatic
    -0.07
     et
    -0.06
    etched
    -0.06
    POSITIVE LOGITS
     мебель
    0.09
     Homer
    0.09
     provinc
    0.09
     تولید
    0.08
     Mozart
    0.08
     عرضه
    0.08
     fornecedores
    0.08
     انتظام
    0.08
     бойынша
    0.08
     зарп
    0.08
    Activations Density 0.000%

    No Known Activations