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. 76076
    Prev
    Next
    INDEX
    Explanations

    capsaicin

    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
    Df
    -0.07
     portal
    -0.07
    pto
    -0.07
     началь
    -0.07
     bz
    -0.07
     asm
    -0.07
     pls
    -0.07
     /↵
    -0.07
     arque
    -0.07
     нач
    -0.07
    POSITIVE LOGITS
     ప్రయ
    0.09
    %B
    0.08
     참가
    0.08
     여행
    0.08
    370
    0.08
     температура
    0.08
     Abrams
    0.07
    Clark
    0.07
     exklus
    0.07
    ั่น
    0.07
    Activations Density 0.002%

    No Known Activations