© 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. 11-RESID-POST-AA
    11. 110777
    Prev
    Next
    INDEX
    Explanations

    Y

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     teg
    -0.07
    trainer
    -0.07
     illusions
    -0.07
    лян
    -0.07
     Wol
    -0.07
    Globals
    -0.07
     Samson
    -0.07
     Terra
    -0.07
    -0.07
     herm
    -0.07
    POSITIVE LOGITS
    末
    0.09
     verte
    0.08
     služby
    0.08
     dossiers
    0.08
     �
    0.07
    =format
    0.07
     $("#"
    0.07
     verfüg
    0.07
     সালের
    0.07
    \t
    0.07
    Activations Density 0.001%
    No Known Activations