© 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. 19-RESID-POST-AA
    11. 19051
    Prev
    Next
    INDEX
    Explanations

    URLs and code snippets

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     πιο
    -0.09
     এপ্রিল
    -0.08
     স্কুল
    -0.08
     услуги
    -0.08
     বেশি
    -0.08
     ফোন
    -0.07
     courir
    -0.07
    蝶
    -0.07
     শেখ
    -0.07
     ঘণ্ট
    -0.07
    POSITIVE LOGITS
     dovrebbe
    0.08
    Facade
    0.07
    Glob
    0.07
    STRACT
    0.07
    ']).
    0.07
     should
    0.07
     과정
    0.07
    <Json
    0.07
    '
    0.07
    British
    0.07
    Activations Density 0.000%

    No Known Activations