© 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. 21511
    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
     tables
    -0.12
    Tables
    -0.12
     Tables
    -0.12
     tablas
    -0.11
     табли
    -0.11
    _tables
    -0.11
     tabel
    -0.11
     table
    -0.11
    .table
    -0.11
    .tables
    -0.10
    POSITIVE LOGITS
     GDPR
    0.24
     Reglamento
    0.17
    欧洲
    0.16
     regulations
    0.16
     Regulations
    0.15
     europeo
    0.14
     欧洲
    0.14
     European
    0.14
     EU
    0.14
     europe
    0.14
    Activations Density 0.018%

    No Known Activations