© 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 EvalsExportsAPI 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. 69213
    Prev
    Next
    INDEX
    Explanations

    angles and rotation

    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
    .yml
    -0.10
     semen
    -0.08
    urement
    -0.08
    ദ്യ
    -0.08
    ദ
    -0.08
     yara
    -0.08
     പട്ട
    -0.08
    双方
    -0.08
    Trials
    -0.07
     corners
    -0.07
    POSITIVE LOGITS
     상승
    0.10
     longitude
    0.09
    Longitude
    0.08
     servo
    0.08
     hue
    0.08
     hourly
    0.08
     incre
    0.08
     reclining
    0.08
     Longitude
    0.08
     radians
    0.08
    Activations Density 0.009%

    No Known Activations