© 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. 22185
    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
     Their
    -0.10
    their
    -0.10
     Их
    -0.09
     their
    -0.09
    Their
    -0.09
     kanilang
    -0.09
     তাদের
    -0.09
     niiden
    -0.09
     іх
    -0.09
     migrate
    -0.09
    POSITIVE LOGITS
     engagement
    0.15
     involvement
    0.15
     outreach
    0.14
    -eng
    0.14
     Engagement
    0.14
    -based
    0.13
     Outreach
    0.12
     service
    0.11
    -level
    0.11
     development
    0.11
    Activations Density 0.013%

    No Known Activations