© 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. 110578
    Prev
    Next
    INDEX
    Explanations

    prepositions or relative 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
     багато
    -0.09
     कई
    -0.08
    мун
    -0.08
     kilka
    -0.07
     многое
    -0.07
     wiele
    -0.07
    JL
    -0.07
     несколько
    -0.07
     למש
    -0.07
     multa
    -0.07
    POSITIVE LOGITS
     women
    0.09
     যারা
    0.09
    abetes
    0.09
    (predicate
    0.08
     builtin
    0.08
     الذين
    0.08
     вообще
    0.08
     additionally
    0.08
    िस
    0.08
     taps
    0.08
    Activations Density 0.050%

    No Known Activations