© 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. 22188
    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
     farming
    -0.08
    -0.08
     informal
    -0.08
     Farming
    -0.07
     bushes
    -0.07
     Forums
    -0.07
    forums
    -0.07
     forums
    -0.07
     comprimento
    -0.07
     Habitat
    -0.07
    POSITIVE LOGITS
     tracer
    0.21
     fluorescent
    0.18
     trac
    0.17
     intraven
    0.16
    Tracer
    0.16
     dyes
    0.16
     radioactive
    0.16
     dye
    0.16
     labeling
    0.15
    -labelled
    0.15
    Activations Density 0.005%
    No Known Activations