© 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. 19484
    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
     Our
    -0.11
     మా
    -0.10
     우리의
    -0.10
    (any
    -0.10
    _any
    -0.10
     ಯಾವುದೇ
    -0.10
     unsere
    -0.10
     podendo
    -0.10
     हमारी
    -0.10
     нашего
    -0.10
    POSITIVE LOGITS
     you're
    0.17
     þú
    0.14
     אתה
    0.13
     you
    0.13
     você
    0.11
    You're
    0.11
    you're
    0.11
     אתם
    0.10
     it's
    0.10
     You're
    0.10
    Activations Density 0.004%

    No Known Activations