© 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 EvalsExportsAPI 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. 20850
    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
     we
    -0.08
     you
    -0.08
     youve
    -0.08
     предп
    -0.08
     havent
    -0.07
    EVER
    -0.07
     latest
    -0.07
     I
    -0.07
     there's
    -0.07
     you'll
    -0.07
    POSITIVE LOGITS
     [...]↵↵
    0.10
     where
    0.10
    ....↵↵
    0.09
     למצ
    0.09
    [...]↵↵
    0.09
     حيث
    0.09
    iedy
    0.09
     अश
    0.09
     as
    0.09
     donde
    0.09
    Activations Density 0.002%

    No Known Activations