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. 49287
    Prev
    Next
    INDEX
    Explanations

    Bot output structure

    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
     неизвест
    -0.08
     sharp
    -0.08
     WOR
    -0.08
     inn
    -0.08
     ужас
    -0.08
     exponential
    -0.08
     металличес
    -0.08
     aon
    -0.07
     Mp
    -0.07
     массива
    -0.07
    POSITIVE LOGITS
    玩
    0.11
     playful
    0.10
     玩
    0.10
    玩的
    0.09
    怎么玩
    0.09
    emoji
    0.09
    玩吗
    0.08
    遊
    0.08
    (logger
    0.08
     jugando
    0.08
    Activations Density 0.008%

    No Known Activations