© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 94817
    Prev
    Next
    INDEX
    Explanations

    Data/calculations

    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
    涵
    -0.08
    倍
    -0.08
    俗
    -0.08
    比例
    -0.08
     النمو
    -0.08
    来的
    -0.08
     Nelson
    -0.07
    /front
    -0.07
    viyy
    -0.07
    宏
    -0.07
    POSITIVE LOGITS
    gesund
    0.08
     Tob
    0.08
    arpa
    0.07
    guard
    0.07
    -care
    0.07
     technische
    0.07
     অতিথ
    0.07
    Seb
    0.07
    Selective
    0.07
     διε
    0.07
    Activations Density 0.025%

    No Known Activations