© 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. 113253
    Prev
    Next
    INDEX
    Explanations

    trace

    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
     clubes
    -0.09
     LIC
    -0.08
    _formula
    -0.08
     seats
    -0.08
     �
    -0.08
     Os
    -0.07
     Licence
    -0.07
     Formula
    -0.07
     bowls
    -0.07
    

↵
    -0.07
    POSITIVE LOGITS
     tracing
    0.11
    trace
    0.10
    .trace
    0.10
    	trace
    0.10
    .Trace
    0.10
    (trace
    0.09
     traced
    0.09
    日志
    0.09
    记录
    0.09
     trace
    0.08
    Activations Density 0.001%

    No Known Activations