© 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. 110717
    Prev
    Next
    INDEX
    Explanations

    Qualifying

    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
     руководство
    -0.08
     lý
    -0.08
    pios
    -0.07
    (balance
    -0.07
    Characteristics
    -0.07
     الاست
    -0.07
     blanket
    -0.07
    ಿಯಾದ
    -0.07
    Representative
    -0.07
     thy
    -0.07
    POSITIVE LOGITS
    名前
    0.09
    期限
    0.08
    timeofday
    0.08
    	names
    0.08
     zab
    0.07
     多
    0.07
    多
    0.07
    讨论
    0.07
     名前
    0.07
    版
    0.07
    Activations Density 0.001%

    No Known Activations