© 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. 19229
    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
    시에
    -0.08
     ;;
    -0.08
    ，就是
    -0.08
    就是
    -0.08
     چیست
    -0.08
    ованием
    -0.08
    :$
    -0.08
    compan
    -0.08
     ,↵↵
    -0.08
     Himself
    -0.08
    POSITIVE LOGITS
     we
    0.19
     they
    0.14
     we've
    0.14
     you
    0.13
     it's
    0.13
     the
    0.13
     we're
    0.13
     they've
    0.13
     আমরা
    0.13
     આપણે
    0.12
    Activations Density 0.008%

    No Known Activations