© 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. 19510
    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
     ואף
    -0.10
     nnyo
    -0.09
     isempty
    -0.09
     twijfel
    -0.09
     akár
    -0.09
    anfaatkan
    -0.09
     воспользоваться
    -0.09
    兩
    -0.08
    יכולת
    -0.08
     utiliser
    -0.08
    POSITIVE LOGITS
    :↵↵
    0.12
     yields
    0.11
     components
    0.10
     ได้แก่
    0.10
    :↵
    0.10
     gồm
    0.09
     =↵
    0.09
     comprising
    0.09
     outputs
    0.09
    _components
    0.09
    Activations Density 0.066%

    No Known Activations