© 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 EvalsExportsinterp-engineNEWAPI 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. 51757
    Prev
    Next
    INDEX
    Explanations

    Arabic poetry

    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
    Arrow
    -0.08
     ROCK
    -0.08
    .Y
    -0.08
    フォ
    -0.08
     cone
    -0.08
    ヴィ
    -0.08
     marcar
    -0.08
     krist
    -0.07
     skeletal
    -0.07
    Rock
    -0.07
    POSITIVE LOGITS
     لفظ
    0.13
     وزن
    0.12
     مقام
    0.12
     أبي
    0.12
     قوله
    0.11
     الوزن
    0.11
     حذف
    0.10
     بيت
    0.10
     كلام
    0.10
     البيت
    0.10
    Activations Density 0.007%

    No Known Activations