© 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. 22059
    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
     rigorous
    -0.08
    Configuration
    -0.08
     configuration
    -0.08
     guards
    -0.08
     Configuration
    -0.07
     provisional
    -0.07
    configuration
    -0.07
     simplest
    -0.07
     resting
    -0.07
     method
    -0.07
    POSITIVE LOGITS
    -focused
    0.18
    -centric
    0.14
     focus
    0.12
    /local
    0.12
    -oriented
    0.12
    focus
    0.12
    -aware
    0.11
    _focus
    0.11
    -events
    0.11
     geographically
    0.11
    Activations Density 0.014%

    No Known Activations