© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 18115
    Prev
    Next
    INDEX
    Explanations

    **

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     There
    -0.10
    ，它
    -0.09
     Assuming
    -0.09
     لاءِ
    -0.09
     Without
    -0.09
     ਲਈ
    -0.09
     ಅದು
    -0.09
    ，该
    -0.09
    -With
    -0.09
    mediately
    -0.09
    POSITIVE LOGITS
     including
    0.13
     включая
    0.13
    including
    0.12
    包括
    0.12
     כגון
    0.12
     incluindo
    0.12
     כולל
    0.11
     incluyendo
    0.11
     einschließlich
    0.11
     ได้แก่
    0.11
    Activations Density 0.042%

    No Known Activations