© 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. 113184
    Prev
    Next
    INDEX
    Explanations

    nebula

    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
     Taschen
    -0.09
    úng
    -0.09
    .Swing
    -0.08
     aten
    -0.08
     dors
    -0.08
     empresas
    -0.08
     üstün
    -0.08
     entreprises
    -0.07
     Dial
    -0.07
    률
    -0.07
    POSITIVE LOGITS
     colorful
    0.09
     carn
    0.08
     vibrant
    0.08
     סער
    0.08
     kleurr
    0.08
     Isaiah
    0.08
    osity
    0.08
     swirling
    0.08
    ;color
    0.07
    -blue
    0.07
    Activations Density 0.002%

    No Known Activations