© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 70602
    Prev
    Next
    INDEX
    Explanations

    inventory, beginning, ending

    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
    Not in Any Lists

    No Comments

    Negative Logits
     يقدم
    -0.08
    �
    -0.07
     aerodynamic
    -0.07
     discomfort
    -0.07
     Ví
    -0.07
     QWidget
    -0.07
     música
    -0.07
     视频
    -0.07
     hyper
    -0.07
    aż
    -0.07
    POSITIVE LOGITS
    前年
    0.09
    elijkse
    0.09
     snapshot
    0.09
     year's
    0.09
    平成
    0.09
    Reporting
    0.09
    余额
    0.09
    前年差
    0.08
    Reported
    0.08
    去年
    0.08
    Activations Density 0.011%

    No Known Activations