© 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. 48955
    Prev
    Next
    INDEX
    Explanations

    say "т"

    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
    zere
    -0.08
    onzo
    -0.08
    delingen
    -0.08
     Due
    -0.08
     Sing
    -0.08
    oxide
    -0.07
    fname
    -0.07
    zul
    -0.07
    mero
    -0.07
    zf
    -0.07
    POSITIVE LOGITS
    т
    0.08
    مكان
    0.08
    Ты
    0.08
     legislators
    0.08
    .Initialize
    0.08
    Initialize
    0.07
    ploy
    0.07
    คุณ
    0.07
    ുണ്ട
    0.07
     phyt
    0.07
    Activations Density 0.000%

    No Known Activations