© 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. 19676
    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
     மற்றும்
    -0.13
     ಅನ್ನು
    -0.11
    -Level
    -0.11
    -Based
    -0.11
     및
    -0.11
     ਅਤੇ
    -0.11
     యొక్క
    -0.11
     અને
    -0.11
    ings
    -0.11
     ಮತ್ತು
    -0.11
    POSITIVE LOGITS
     the
    0.22
     their
    0.20
     a
    0.17
     an
    0.17
     its
    0.16
     these
    0.15
     some
    0.15
     those
    0.14
     appropriate
    0.14
     various
    0.13
    Activations Density 0.030%

    No Known Activations