© 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. 23-RESID-POST-AA
    11. 52274
    Prev
    Next
    INDEX
    Explanations

    PHP configuration files

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     queryset
    -0.10
     bearer
    -0.09
     $('[
    -0.09
     steward
    -0.09
    	redirect
    -0.09
    $where
    -0.09
    \Models
    -0.08
    $model
    -0.08
    	cs
    -0.08
    sequelize
    -0.08
    POSITIVE LOGITS
     ini
    0.12
     zend
    0.10
     pc
    0.10
     PHP
    0.10
     Ini
    0.10
    (memory
    0.10
    _ini
    0.10
     php
    0.10
     PE
    0.09
    php
    0.09
    Activations Density 0.008%

    No Known Activations