© 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. 22799
    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
     desgaste
    -0.08
     komplik
    -0.08
    цией
    -0.08
    熟女
    -0.08
     ʻano
    -0.08
     abnormalities
    -0.08
     সপ্ত
    -0.08
     hass
    -0.08
    hrase
    -0.07
    parator
    -0.07
    POSITIVE LOGITS
     funding
    0.47
    资金
    0.42
     Funding
    0.40
    Funding
    0.39
     निध
    0.36
     financement
    0.36
     financiación
    0.36
     financiamento
    0.34
     funded
    0.33
     funds
    0.33
    Activations Density 0.130%

    No Known Activations