© 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. 70108
    Prev
    Next
    INDEX
    Explanations

    reflexive pronouns

    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
    -0.07
     Limp
    -0.07
     Pf
    -0.07
     провод
    -0.07
     الج
    -0.07
     Zip
    -0.07
     наруш
    -0.07
     tilfred
    -0.07
     syringe
    -0.07
     Paran
    -0.07
    POSITIVE LOGITS
    เอง
    0.12
    自身
    0.09
     뿐
    0.09
     sendiri
    0.09
    -même
    0.09
    뿐
    0.09
    以及
    0.09
     personally
    0.09
    /from
    0.09
     mình
    0.08
    Activations Density 0.122%
    No Known Activations