© 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. 22177
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     Mitgl
    -0.09
     իրական
    -0.09
     հեշտ
    -0.09
     համակարգ
    -0.09
     അനുവ
    -0.09
     հնար
    -0.09
     նոյ
    -0.09
     տրամ
    -0.09
     վնաս
    -0.09
     մարմ
    -0.08
    POSITIVE LOGITS
    often
    0.09
    FONT
    0.09
    such
    0.08
    .'</
    0.08
    .''↵↵
    0.08
    which
    0.08
    _FONT
    0.08
    ắ
    0.08
    .font
    0.08
     único
    0.07
    Activations Density 0.000%

    No Known Activations