© 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. 8033
    Prev
    Next
    INDEX
    Explanations

    code/mathematical expressions

    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
     Prophet
    -0.09
     richten
    -0.08
    omer
    -0.08
    ")↵↵↵
    -0.08
     Exhibit
    -0.07
     Peek
    -0.07
     Eller
    -0.07
     blocker
    -0.07
     Sheldon
    -0.07
     Apostle
    -0.07
    POSITIVE LOGITS
    ึก
    0.09
     aansprak
    0.08
     кислот
    0.08
    /AIDS
    0.08
     أدى
    0.08
     bals
    0.08
     يشعر
    0.08
     인해
    0.07
     એટ
    0.07
     ક્યાં
    0.07
    Activations Density 0.000%

    No Known Activations