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. 44096
    Prev
    Next
    INDEX
    Explanations

    of

    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
    ංග
    -0.08
    cimento
    -0.08
     hinein
    -0.08
     wholeheartedly
    -0.08
    raiser
    -0.08
     abi
    -0.08
     Genius
    -0.08
     disposit
    -0.07
     постепенно
    -0.07
    plastic
    -0.07
    POSITIVE LOGITS
     DAL
    0.08
     कहीं
    0.08
     Bly
    0.08
     suburb
    0.08
    地点
    0.08
     Der
    0.08
    neath
    0.07
    附近
    0.07
    Dal
    0.07
     headquartered
    0.07
    Activations Density 0.059%

    No Known Activations