© 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. 22282
    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
     λεπ
    -0.08
     المذك
    -0.07
     معرفة
    -0.07
     IU
    -0.07
     sides
    -0.07
    ore
    -0.06
    otrop
    -0.06
    ohen
    -0.06
    ogene
    -0.06
     tiro
    -0.06
    POSITIVE LOGITS
     إحدى
    0.21
     egyik
    0.20
     eldest
    0.19
     ensimmä
    0.19
     largest
    0.19
    첫
    0.19
     সবচ
    0.18
    第
    0.18
     첫
    0.18
    largest
    0.17
    Activations Density 0.157%

    No Known Activations