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

    Neuronpedia

    APICircuit 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. 88293
    Prev
    Next
    INDEX
    Explanations

    German language

    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
    .Once
    -0.08
     खुश
    -0.07
     yardım
    -0.07
     yordam
    -0.07
     synchronous
    -0.07
     ingenious
    -0.07
     పంప
    -0.07
     счастлив
    -0.07
    同步
    -0.07
    PSC
    -0.07
    POSITIVE LOGITS
    全文
    0.09
     articol
    0.09
     flera
    0.09
     നിരവധി
    0.09
     español
    0.09
     pasted
    0.08
     kostet
    0.08
     több
    0.08
     Various
    0.08
     above
    0.08
    Activations Density 0.019%

    No Known Activations