© 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. 23060
    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
    Negative Logits
    ்க்க
    -0.08
     announcements
    -0.08
    _NAME
    -0.08
     considerably
    -0.08
     publicação
    -0.08
    гуул
    -0.08
     publication
    -0.08
     confirmation
    -0.08
     prominently
    -0.08
    BSITE
    -0.08
    POSITIVE LOGITS
    ouncer
    0.11
    uaire
    0.11
    ouncing
    0.11
    unzi
    0.11
    ouncements
    0.11
    unciation
    0.11
    ährend
    0.10
    iversaire
    0.10
    ounced
    0.10
    exe
    0.10
    Activations Density 0.005%

    No Known Activations