© 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. 22704
    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
     >=
    -0.09
     >
    -0.08
    Multiple
    -0.08
     <=
    -0.08
    Interested
    -0.07
     multiple
    -0.07
     ≥
    -0.07
     Multiple
    -0.07
    levant
    -0.07
    查看更多
    -0.07
    POSITIVE LOGITS
     permutation
    0.18
     bij
    0.17
     permutations
    0.16
    Permutation
    0.14
    bije
    0.14
     exactly
    0.14
     einzigartige
    0.13
     shuffled
    0.13
    bij
    0.13
     uniques
    0.13
    Activations Density 0.066%

    No Known Activations