© 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. 23-RESID-POST-AA
    11. 51561
    Prev
    Next
    INDEX
    Explanations

    say "ry" word

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     athletics
    -0.08
     bury
    -0.08
     prehistoric
    -0.07
     Allgeme
    -0.07
    isul
    -0.07
     exercícios
    -0.07
     PHY
    -0.07
     Athletics
    -0.07
     fotografie
    -0.07
    TPL
    -0.07
    POSITIVE LOGITS
    rying
    0.14
    ry
    0.13
    ryer
    0.12
    ried
    0.11
    izziness
    0.11
    ుడ్
    0.10
    RY
    0.10
    izzes
    0.10
    ats
    0.09
    ूड
    0.09
    Activations Density 0.019%

    No Known Activations