© 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. 25007
    Prev
    Next
    INDEX
    Explanations

    bracket tokens

    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
    ैत
    -0.07
     fried
    -0.07
     Inspir
    -0.07
    buds
    -0.07
     religi
    -0.07
     soulful
    -0.07
     buds
    -0.07
     insect
    -0.07
    ixed
    -0.07
     rocket
    -0.07
    POSITIVE LOGITS
     통한
    0.08
     overhaul
    0.08
    Damit
    0.07
     Damit
    0.07
     certes
    0.07
     Dining
    0.07
     dining
    0.07
    /met
    0.07
     Met
    0.07
    ование
    0.07
    Activations Density 0.029%

    No Known Activations