© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 95872
    Prev
    Next
    INDEX
    Explanations

    server locations and data

    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
     взыск
    -0.08
     Plast
    -0.08
    ujar
    -0.08
     Solution
    -0.08
     สม
    -0.07
     competency
    -0.07
     fruition
    -0.07
    Level
    -0.07
     Schools
    -0.07
    ome
    -0.07
    POSITIVE LOGITS
     geographically
    0.09
     caches
    0.08
     latency
    0.08
     verfügbar
    0.08
     beschikbaar
    0.08
    ternet
    0.08
     mounted
    0.08
     locations
    0.08
     DNS
    0.08
     deployed
    0.08
    Activations Density 0.008%

    No Known Activations