© 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. 21145
    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
     latter
    -0.09
     Probably
    -0.08
     provavelmente
    -0.08
     probablement
    -0.08
     predominantly
    -0.08
     aikaan
    -0.08
     vermutlich
    -0.08
     ?,
    -0.07
     \(
    -0.07
    probably
    -0.07
    POSITIVE LOGITS
     any
    0.20
     orice
    0.18
     potential
    0.18
     لأي
    0.18
    任何
    0.17
     nenpòt
    0.17
     cualquier
    0.17
     possible
    0.17
     nuances
    0.17
     if
    0.17
    Activations Density 0.036%

    No Known Activations