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. 11715
    Prev
    Next
    INDEX
    Explanations

    Storage expansion

    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
     Eli
    -0.08
    elin
    -0.08
    é
    -0.08
    -production
    -0.07
     visc
    -0.07
    ire
    -0.07
    Printing
    -0.07
    Production
    -0.07
    -0.07
     production
    -0.07
    POSITIVE LOGITS
    Expandable
    0.10
     รอง
    0.10
    扩
    0.09
     슬롯
    0.08
     externa
    0.08
    外挂
    0.08
     uitbreiding
    0.08
     இல்லை
    0.08
     expandable
    0.08
     notebooks
    0.08
    Activations Density 0.011%

    No Known Activations