© 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. 19-RESID-POST-AA
    11. 18654
    Prev
    Next
    INDEX
    Explanations

    mathematical formulas

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    хыра
    -0.11
    ԥсы
    -0.11
    ахеит
    -0.11
    ьақә
    -0.11
    ҭах
    -0.11
    ҿи
    -0.11
    ҭаа
    -0.11
    ҳаҭ
    -0.11
    ҵә
    -0.11
    ырҭ
    -0.11
    POSITIVE LOGITS
     Tage
    0.08
    ),
    0.07
     일
    0.07
     constants
    0.07
     kaynak
    0.07
     그
    0.07
     -
    0.07
     Foundation
    0.07
    日
    0.07
     etc
    0.07
    Activations Density 0.186%

    No Known Activations