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

    Neuronpedia

    Jacobian LensNEW
    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. 49392
    Prev
    Next
    INDEX
    Explanations

    编

    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
    isir
    -0.09
    is
    -0.09
    icular
    -0.09
    Island
    -0.08
     AWD
    -0.07
    ulk
    -0.07
    ilibr
    -0.07
    -sa
    -0.07
     Satell
    -0.07
    -vis
    -0.07
    POSITIVE LOGITS
    码
    0.11
    وره
    0.10
    عوبة
    0.10
    ي
    0.09
    ادرات
    0.09
    碼
    0.08
    ומת
    0.08
    หมด
    0.08
    ور
    0.08
    ورها
    0.08
    Activations Density 0.001%

    No Known Activations