© 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. 112427
    Prev
    Next
    INDEX
    Explanations

    cocoa

    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
    .Emp
    -0.08
    attung
    -0.08
    .Tick
    -0.08
     sakin
    -0.08
     UAV
    -0.07
    》（
    -0.07
     GPS
    -0.07
    -лет
    -0.07
    arium
    -0.07
    agaan
    -0.07
    POSITIVE LOGITS
     فوت
    0.09
     NSLayout
    0.08
     Kot
    0.08
    实现
    0.08
     Radeon
    0.08
     strenuous
    0.08
     unat
    0.08
     dropout
    0.07
    Kot
    0.07
     hookup
    0.07
    Activations Density 0.007%

    No Known Activations