© 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. 20787
    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
     Beyond
    -0.11
     beyond
    -0.11
    不仅
    -0.11
    Beyond
    -0.11
     ondanks
    -0.10
     jangan
    -0.10
     oltre
    -0.09
     bukan
    -0.09
     δεν
    -0.09
     versus
    -0.09
    POSITIVE LOGITS
     vielmehr
    0.20
    む
    0.12
     гораздо
    0.12
     instead
    0.11
     మాత్రం
    0.11
     istället
    0.11
    。所以
    0.10
     ones
    0.10
     prostu
    0.10
     malah
    0.10
    Activations Density 0.194%

    No Known Activations