© 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. 3-RESID-POST-AA
    11. 13188
    Prev
    Next
    INDEX
    Explanations

    числа

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     hö
    -0.08
    Jan
    -0.08
    gay
    -0.07
     lite
    -0.07
     Ende
    -0.07
     Jan
    -0.07
     Mitchell
    -0.07
    lite
    -0.07
    ع
    -0.07
     Trans
    -0.07
    POSITIVE LOGITS
     prac
    0.08
     prick
    0.08
    racha
    0.07
     oy
    0.07
     polys
    0.07
    _PAY
    0.07
     sü
    0.07
     tú
    0.07
    束
    0.07
     Potter
    0.07
    Activations Density 0.003%

    No Known Activations