© 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. 11-RESID-POST-AA
    11. 110409
    Prev
    Next
    INDEX
    Explanations

    问

    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
    生态
    -0.09
     Artemis
    -0.08
     Liberia
    -0.08
     �
    -0.08
     Ghana
    -0.08
     Kenyan
    -0.08
     domina
    -0.08
     ecosystems
    -0.08
     boon
    -0.08
     Zimbabwe
    -0.08
    POSITIVE LOGITS
    oque
    0.08
     الأمر
    0.07
    »,
    0.07
    Pagination
    0.07
    وائد
    0.07
    ¸
    0.07
     "',
    0.07
     قالب
    0.07
    -pagination
    0.07
     الصفحة
    0.07
    Activations Density 0.232%

    No Known Activations