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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 44685
    Prev
    Next
    INDEX
    Explanations

    tape

    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
    Window
    -0.09
     muffin
    -0.09
     disf
    -0.09
    JUnit
    -0.08
    _window
    -0.08
    ARGET
    -0.08
     cupc
    -0.08
     window
    -0.08
     Ace
    -0.08
     WINDOW
    -0.08
    POSITIVE LOGITS
     preparing
    0.08
     alimentação
    0.07
     feed
    0.07
    高度
    0.07
     तैयारी
    0.07
     VSI
    0.07
    (feed
    0.07
     오는
    0.07
    ベル
    0.07
     prepared
    0.07
    Activations Density 0.002%

    No Known Activations