© 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. 17991
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
     publicité
    -0.08
    -down
    -0.08
     দিনে
    -0.08
    ??↵↵
    -0.08
    -facebook
    -0.07
     ánh
    -0.07
    ?",↵
    -0.07
    -'
    -0.07
     minimal
    -0.07
     signage
    -0.07
    POSITIVE LOGITS
     skyscr
    0.11
     journalists
    0.11
     टूट
    0.11
     기자
    0.11
     guest
    0.10
    记者
    0.10
     पत्रकार
    0.10
     journalistes
    0.10
    Broken
    0.10
     журналист
    0.10
    Activations Density 0.005%

    No Known Activations