© 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. 21454
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    аҭ
    -0.19
    иаа
    -0.19
    егь
    -0.19
    ырха
    -0.19
    天堂网
    -0.19
    азаара
    -0.19
    охойн
    -0.19
    ынтә
    -0.19
    әса
    -0.19
    арҭ
    -0.19
    POSITIVE LOGITS
     активно
    0.14
     сформ
    0.13
     самостоятельно
    0.12
     properly
    0.12
     существенно
    0.12
     постепенно
    0.12
     подробно
    0.11
     позвол
    0.11
     вы
    0.11
     secara
    0.11
    Activations Density 0.055%

    No Known Activations