© 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. 21151
    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
    öss
    -0.08
     Teilnahme
    -0.08
     presentada
    -0.08
    Being
    -0.08
     zusätzliche
    -0.08
    teg
    -0.08
    being
    -0.07
     übersch
    -0.07
     serà
    -0.07
     apresentada
    -0.07
    POSITIVE LOGITS
     ever
    0.09
     أمري
    0.09
     уме
    0.09
     who
    0.09
     سعود
    0.08
     שמ
    0.08
     считают
    0.08
     current
    0.08
    .current
    0.08
     actuales
    0.08
    Activations Density 0.012%

    No Known Activations