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. 43513
    Prev
    Next
    INDEX
    Explanations

    herself

    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
     è
    -0.08
     maggiore
    -0.07
    Poss
    -0.07
     possession
    -0.07
    éter
    -0.07
    ラン
    -0.07
     shuffle
    -0.07
     gps
    -0.07
    Masters
    -0.07
     randomness
    -0.07
    POSITIVE LOGITS
     mä
    0.09
     xaq
    0.09
     perched
    0.08
     tiện
    0.08
    偷拍
    0.08
     montaje
    0.08
    ויד
    0.08
     parha
    0.08
     Mounted
    0.08
     معل
    0.08
    Activations Density 0.001%

    No Known Activations