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. 111716
    Prev
    Next
    INDEX
    Explanations

    mother

    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
     Guys
    -0.09
     Rangers
    -0.08
    érico
    -0.08
     ule
    -0.08
    cente
    -0.08
     amino
    -0.08
     ue
    -0.07
    بور
    -0.07
    Guys
    -0.07
     sho
    -0.07
    POSITIVE LOGITS
    님의
    0.09
    ם
    0.08
     instinct
    0.08
    �
    0.07
    hesis
    0.07
    님
    0.07
    -school
    0.07
    embe
    0.07
    聚
    0.07
    ाच्या
    0.07
    Activations Density 0.021%

    No Known Activations