© 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. 22761
    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
     subscrib
    -0.08
    atrices
    -0.07
     directives
    -0.07
    ￥
    -0.07
     cáps
    -0.07
    apak
    -0.07
     subscribe
    -0.07
    Flg
    -0.07
     dönem
    -0.07
     Subscription
    -0.07
    POSITIVE LOGITS
     distributions
    0.33
     distribution
    0.33
     distribuição
    0.30
    Distribution
    0.30
     Distribution
    0.29
    _distribution
    0.29
    distribution
    0.29
     distribución
    0.29
     वितरण
    0.28
     распредел
    0.25
    Activations Density 0.032%

    No Known Activations