© 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. 21662
    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
    onyme
    -0.08
     fertile
    -0.08
     regenerate
    -0.08
     diu
    -0.08
     ued
    -0.08
     falar
    -0.08
    uvi
    -0.07
     organismo
    -0.07
    ctype
    -0.07
     regenerated
    -0.07
    POSITIVE LOGITS
    -related
    0.14
     allocation
    0.10
     allocations
    0.10
    -specific
    0.10
     portion
    0.09
    nasium
    0.09
     purposes
    0.09
     expenditures
    0.09
     costing
    0.09
     alone
    0.09
    Activations Density 0.052%

    No Known Activations