© 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. 18282
    Prev
    Next
    INDEX
    Explanations

    quantity

    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
    第一
    -0.09
    첫
    -0.09
     第一
    -0.08
    और
    -0.08
     Grü
    -0.08
     첫
    -0.08
     origins
    -0.08
     그리고
    -0.08
    Issuer
    -0.08
    文本
    -0.08
    POSITIVE LOGITS
     quantity
    0.08
     Quantity
    0.08
     salary
    0.08
    ))
    0.08
     вес
    0.08
     مبلغ
    0.08
     Amount
    0.08
    Quantity
    0.08
     كمية
    0.08
     monetary
    0.08
    Activations Density 0.005%

    No Known Activations