© 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. 21649
    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
     be
    -0.09
    ்களை
    -0.09
     actual
    -0.08
     както
    -0.08
    ்கள்
    -0.08
    ்களில்
    -0.08
    filters
    -0.08
    )(
    -0.08
    λία
    -0.07
     illetve
    -0.07
    POSITIVE LOGITS
     단계
    0.10
     შემთხვევაში
    0.10
     Abschnitt
    0.09
     ಮಟ್ಟ
    0.09
     ഭാഗ
    0.09
     ক্ষেত্রে
    0.09
     occas
    0.09
    илет
    0.09
     स्तर
    0.09
     objectively
    0.09
    Activations Density 0.106%

    No Known Activations