© 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. 18173
    Prev
    Next
    INDEX
    Explanations

    credit card numbers

    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
    Negative Logits
    主要
    -0.08
    тан
    -0.08
    Segoe
    -0.08
    Axes
    -0.07
    зура
    -0.07
    ding
    -0.07
    copyright
    -0.07
     coordinates
    -0.07
    Coords
    -0.07
    BST
    -0.07
    POSITIVE LOGITS
    評価
    0.08
    -With
    0.08
     évalu
    0.08
     bekannte
    0.08
     valut
    0.08
    غيل
    0.08
    _make
    0.07
     Evaluate
    0.07
     بلد
    0.07
    ڑ
    0.07
    Activations Density 0.000%

    No Known Activations