© 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. 50287
    Prev
    Next
    INDEX
    Explanations

    hiking trails

    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
    生产
    -0.09
     Produktions
    -0.09
    生活
    -0.09
     dzī
    -0.09
     voyages
    -0.09
    .production
    -0.09
     उत्पादन
    -0.08
    住房
    -0.08
    .delivery
    -0.08
     Auctions
    -0.08
    POSITIVE LOGITS
     trail
    0.17
     strenuous
    0.15
     trails
    0.15
    Trail
    0.15
    trail
    0.15
     Trail
    0.14
     loop
    0.13
    loop
    0.13
     hike
    0.13
     Reykj
    0.13
    Activations Density 0.034%

    No Known Activations