© 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. 18202
    Prev
    Next
    INDEX
    Explanations

    Prepositions leading to phrases

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .
    -0.09
     need
    -0.09
    .↵↵
    -0.08
    Needed
    -0.08
     didn't
    -0.08
     нуж
    -0.08
     multiplied
    -0.08
     used
    -0.07
     +
    -0.07
     ways
    -0.07
    POSITIVE LOGITS
    ৃষ্ঠ
    0.10
    such
    0.09
     ramach
    0.09
    0.09
    []){↵
    0.09
    Such
    0.08
     okviru
    0.08
    ){↵//
    0.08
     ){↵
    0.08
    ണക്ക
    0.08
    Activations Density 0.367%
    No Known Activations