© 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. 18957
    Prev
    Next
    INDEX
    Explanations

    这样

    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
     ضرورة
    -0.10
     لذلك
    -0.09
     이에
    -0.09
     كذلك
    -0.09
     כאן
    -0.08
     ఇంద
    -0.08
     Cependant
    -0.08
    =.*
    -0.08
     Thus
    -0.08
    гин
    -0.08
    POSITIVE LOGITS
     하면
    0.14
     facendo
    0.14
     ensures
    0.13
    做
    0.13
     చేస్త
    0.13
     করলে
    0.12
    才能
    0.11
     avoids
    0.11
     செய்வ
    0.11
    的话
    0.11
    Activations Density 0.003%

    No Known Activations