© 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. 22586
    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
     Pentru
    -0.09
    ��
    -0.08
    ுப
    -0.08
    ため
    -0.08
    Sandbox
    -0.07
    	errors
    -0.07
    imulator
    -0.07
     spreadsheets
    -0.07
     Calend
    -0.07
    usių
    -0.07
    POSITIVE LOGITS
    整个
    0.16
     전체
    0.15
     સમગ્ર
    0.15
     gesamten
    0.15
     entire
    0.14
     gesamte
    0.14
     આખ
    0.14
    전체
    0.14
     totalité
    0.13
     дли
    0.13
    Activations Density 0.018%

    No Known Activations