© 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. 23-RESID-POST-AA
    11. 49734
    Prev
    Next
    INDEX
    Explanations

    router

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Analysts
    -0.09
     Clipboard
    -0.08
    idue
    -0.08
     infirm
    -0.08
     blasts
    -0.08
     मैदान
    -0.08
     sight
    -0.08
     percussion
    -0.08
    Transpose
    -0.08
     мәй
    -0.08
    POSITIVE LOGITS
     router
    0.32
    router
    0.29
     Router
    0.28
    (router
    0.28
    _router
    0.28
    Router
    0.27
    .router
    0.27
    -router
    0.27
    	router
    0.26
     routers
    0.26
    Activations Density 0.032%

    No Known Activations