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. 56074
    Prev
    Next
    INDEX
    Explanations

    taxes

    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
     abbrevi
    -0.08
     dyst
    -0.08
     rtl
    -0.07
    aturi
    -0.07
     Cull
    -0.07
     societies
    -0.07
     ster
    -0.07
     appear
    -0.07
     Ž
    -0.07
     fade
    -0.07
    POSITIVE LOGITS
    营业
    0.09
     kerül
    0.09
    usaha
    0.08
     entrepreneur
    0.08
     excess
    0.08
    hlah
    0.08
    创业
    0.08
    mittlung
    0.08
     annuel
    0.07
    のみ
    0.07
    Activations Density 0.003%

    No Known Activations