© 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. 30850
    Prev
    Next
    INDEX
    Explanations

    Dragon

    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
    hips
    -0.08
    itures
    -0.08
     leva
    -0.08
     רח
    -0.07
     Myself
    -0.07
     hav
    -0.07
    ॉलर
    -0.07
    HAV
    -0.07
    Nga
    -0.07
    anter
    -0.07
    POSITIVE LOGITS
    дог
    0.09
     делу
    0.08
     decisive
    0.08
     QUEST
    0.08
     cinn
    0.08
    об
    0.08
    十二
    0.08
     Bezug
    0.07
    ресс
    0.07
     capsule
    0.07
    Activations Density 0.003%

    No Known Activations