© 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. 91861
    Prev
    Next
    INDEX
    Explanations

    Unstructured text

    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
    (buffer
    -0.09
    (...)↵
    -0.08
    (events
    -0.08
    (rt
    -0.07
    (vars
    -0.07
    洗
    -0.07
    (args
    -0.07
    (pipe
    -0.07
    (Arrays
    -0.07
    И
    -0.07
    POSITIVE LOGITS
     günlük
    0.08
     night's
    0.08
     Classified
    0.08
     Movers
    0.08
     pokies
    0.08
     unopened
    0.08
    jali
    0.08
     ويا
    0.08
     ingew
    0.08
     财神
    0.08
    Activations Density 0.000%

    No Known Activations