© 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. 18248
    Prev
    Next
    INDEX
    Explanations

    before

    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
    Clicked
    -0.10
    antz
    -0.09
    .has
    -0.08
    _clicked
    -0.08
    .have
    -0.08
    _received
    -0.08
    asure
    -0.08
     иметь
    -0.08
    ਿੱ
    -0.08
     unsolicited
    -0.08
    POSITIVE LOGITS
     final
    0.11
    final
    0.10
     adding
    0.09
     अंतिम
    0.09
     Final
    0.08
    Final
    0.08
     дода
    0.08
    zinye
    0.08
     drugi
    0.08
    adding
    0.08
    Activations Density 0.003%

    No Known Activations