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

    Neuronpedia

    Jacobian LensNEW
    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. 69024
    Prev
    Next
    INDEX
    Explanations

    trigonometry

    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
    .Objects
    -0.09
     Merit
    -0.08
    ocr
    -0.08
    .fields
    -0.07
    Extractor
    -0.07
    (attrs
    -0.07
    改变
    -0.07
    ırım
    -0.07
     Oll
    -0.07
     Designs
    -0.07
    POSITIVE LOGITS
     radians
    0.11
     quadrant
    0.09
     오후
    0.09
     yra
    0.09
     오전
    0.09
     शुक्रवार
    0.09
     বৃহস্পতিবার
    0.09
    Quaternion
    0.09
     жары
    0.09
     anguish
    0.09
    Activations Density 0.038%

    No Known Activations