© 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. 23-RESID-POST-AA
    11. 50535
    Prev
    Next
    INDEX
    Explanations

    散

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Translation
    -0.09
     unsus
    -0.08
     ನಿಧ
    -0.07
     Transl
    -0.07
     transl
    -0.07
    _translation
    -0.07
    Translation
    -0.07
    ém
    -0.07
     mit
    -0.07
    ুস
    -0.07
    POSITIVE LOGITS
    �
    0.11
    射
    0.11
    attering
    0.09
    点
    0.09
    列
    0.09
     점
    0.08
     DASH
    0.08
    焦
    0.08
    attered
    0.08
     �
    0.08
    Activations Density 0.000%

    No Known Activations