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. 106175
    Prev
    Next
    INDEX
    Explanations

    Analytic Hierarchy Process

    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
    eep
    -0.08
    "d
    -0.07
     strict
    -0.07
    (st
    -0.07
     específico
    -0.07
     outlines
    -0.07
     clamp
    -0.07
     Clamp
    -0.07
     chase
    -0.07
    Specific
    -0.07
    POSITIVE LOGITS
     мужчин
    0.09
     phon
    0.08
     gelang
    0.08
     чолов
    0.08
     SWOT
    0.08
     fría
    0.08
     verdeeld
    0.08
     мужч
    0.08
     масш
    0.08
     JU
    0.08
    Activations Density 0.002%

    No Known Activations