© 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. 64740
    Prev
    Next
    INDEX
    Explanations

    code

    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
     rica
    -0.08
    造
    -0.08
     verja
    -0.08
     yards
    -0.08
     Jul
    -0.08
     stor
    -0.08
     труда
    -0.08
     rich
    -0.07
     Rica
    -0.07
    丰富
    -0.07
    POSITIVE LOGITS
    ,current
    0.13
    current
    0.12
     Current
    0.12
    Current
    0.12
    (current
    0.12
     当前
    0.12
    /current
    0.12
    CURRENT
    0.12
     текущ
    0.11
     CURRENT
    0.11
    Activations Density 0.027%

    No Known Activations