© 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. 110379
    Prev
    Next
    INDEX
    Explanations

    just

    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
     �
    -0.08
    (dot
    -0.08
    评级
    -0.08
    illustr
    -0.08
    欧洲
    -0.07
    (|
    -0.07
    幻
    -0.07
    ρί
    -0.07
     enchant
    -0.07
    (primary
    -0.07
    POSITIVE LOGITS
     المسلم
    0.09
     توقف
    0.09
    ِل
    0.08
     مقابل
    0.08
     erled
    0.08
     compromise
    0.08
     بعد
    0.08
    यान
    0.08
     nach
    0.08
     полу
    0.08
    Activations Density 0.000%

    No Known Activations