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. 114009
    Prev
    Next
    INDEX
    Explanations

    telegram bot buttons/code

    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
    先进
    -0.09
     sọ
    -0.08
     impur
    -0.08
    规律
    -0.08
     DSM
    -0.08
    侵
    -0.08
    istika
    -0.08
     whistle
    -0.08
    ệc
    -0.07
     excuse
    -0.07
    POSITIVE LOGITS
    -buttons
    0.12
     botones
    0.12
     버튼
    0.11
    buttons
    0.11
     кноп
    0.11
    Buttons
    0.11
    _buttons
    0.11
    /buttons
    0.10
    按钮
    0.10
     clickable
    0.10
    Activations Density 0.005%

    No Known Activations