© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 23-RESID-POST-AA
    11. 97838
    Prev
    Next
    INDEX
    Explanations

    French pronoun

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     says
    -0.11
     saying
    -0.10
    pos
    -0.10
     pos
    -0.10
    _pos
    -0.10
    [pos
    -0.09
     ότι
    -0.09
    .pos
    -0.09
    (Pos
    -0.09
     said
    -0.09
    POSITIVE LOGITS
     considérer
    0.13
     consideran
    0.13
     considère
    0.13
     juge
    0.13
     estime
    0.12
     estim
    0.12
     considerar
    0.12
     considera
    0.12
     consid
    0.12
     considere
    0.11
    Activations Density 0.005%

    No Known Activations