© 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. 11-RESID-POST-AA
    11. 79168
    Prev
    Next
    INDEX
    Explanations

    writing styles

    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
    _lbl
    -0.09
     공연
    -0.09
     استاد
    -0.09
     کوچ
    -0.08
     ښو
    -0.08
     incontro
    -0.08
     بزر
    -0.08
     სწ
    -0.08
     متخصص
    -0.08
     مهمة
    -0.08
    POSITIVE LOGITS
     punctuation
    0.10
     vocabulary
    0.09
     capitalization
    0.08
     word
    0.08
     tendencies
    0.08
    ysy
    0.08
     sentence
    0.08
     emojis
    0.08
     serif
    0.08
     sent
    0.08
    Activations Density 0.022%

    No Known Activations