© 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. 20932
    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
    _defaults
    -0.08
     modifications
    -0.08
     further
    -0.08
     errors
    -0.07
    enka
    -0.07
    updates
    -0.07
    vik
    -0.07
     mistakes
    -0.07
     betere
    -0.07
     opener
    -0.07
    POSITIVE LOGITS
     URLWith
    0.11
    Selective
    0.10
    Respect
    0.10
    Underlying
    0.10
    Parameterized
    0.10
     sogenannten
    0.10
     zogenaamde
    0.09
     sogenannte
    0.09
     հենց
    0.09
    Limited
    0.09
    Activations Density 0.010%

    No Known Activations