Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 43456
    Prev
    Next
    INDEX
    Explanations

    East Asian languages

    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
     announce
    -0.09
     reopen
    -0.09
    promo
    -0.08
     promotions
    -0.08
     promo
    -0.08
    announce
    -0.08
     renovations
    -0.08
    祝い
    -0.08
     upscale
    -0.08
    ,各
    -0.08
    POSITIVE LOGITS
     Understanding
    0.08
    fasst
    0.08
    Understanding
    0.08
     critique
    0.08
     주장
    0.07
    Simpl
    0.07
     חוק
    0.07
     Later
    0.07
    ān
    0.07
    Later
    0.07
    Activations Density 0.002%

    No Known Activations