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. 45095
    Prev
    Next
    INDEX
    Explanations

    tree

    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
    ಮನ
    -0.09
     bilər
    -0.09
     varsa
    -0.09
     eyikeyi
    -0.09
     ألم
    -0.09
     viento
    -0.09
    imulator
    -0.08
    ವಸ್ಥ
    -0.08
     افت
    -0.08
     purposely
    -0.08
    POSITIVE LOGITS
    0.09
     Geological
    0.08
    作为
    0.08
    施工
    0.08
    (Action
    0.08
    (action
    0.08
    (single
    0.08
    (raw
    0.07
     атом
    0.07
    方案
    0.07
    Activations Density 0.006%

    No Known Activations