© 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. 20584
    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
     millions
    -0.10
     thousands
    -0.09
     огромное
    -0.09
     Thousands
    -0.08
     tonnes
    -0.08
    .False
    -0.08
     dużo
    -0.08
    коп
    -0.08
     হাজার
    -0.08
     Millionen
    -0.08
    POSITIVE LOGITS
    徒歩
    0.11
     errands
    0.09
     downtown
    0.09
     comodidad
    0.09
     Representation
    0.09
     residents
    0.09
    menities
    0.09
     moradores
    0.09
     commuting
    0.09
     household
    0.09
    Activations Density 0.003%

    No Known Activations