© 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 EvalsExportsinterp-engineNEWAPI 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. 110404
    Prev
    Next
    INDEX
    Explanations

    time

    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
    örden
    -0.08
     saver
    -0.08
     ניט
    -0.08
    ಜನಿಕ
    -0.08
     ধরনের
    -0.08
     prácticamente
    -0.07
     praticamente
    -0.07
    ရွ
    -0.07
     방식
    -0.07
     металл
    -0.07
    POSITIVE LOGITS
     thereafter
    0.12
     നടന്ന
    0.09
     Subsequently
    0.09
     afterwards
    0.08
    gam
    0.08
     subsequently
    0.08
    ск
    0.07
     afterward
    0.07
    警方
    0.07
     ঘটে
    0.07
    Activations Density 0.026%

    No Known Activations