© 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. 11-RESID-POST-AA
    11. 71653
    Prev
    Next
    INDEX
    Explanations

    price per unit

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    Toda
    -0.07
    capitalize
    -0.07
    捕
    -0.07
    Reflect
    -0.07
    _pe
    -0.07
     المطل
    -0.07
     capitalize
    -0.07
     teles
    -0.07
    حض
    -0.07
    Nicole
    -0.07
    POSITIVE LOGITS
     Ratio
    0.12
     cheapest
    0.11
     Cost
    0.11
     ratio
    0.11
    ratio
    0.10
     cheaper
    0.10
    .cost
    0.10
     Kosten
    0.09
    _COST
    0.09
     Werbung
    0.09
    Activations Density 0.024%

    No Known Activations