Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 633
    Prev
    Next
    INDEX
    Explanations

    a

    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
     coughing
    -0.09
     experimentally
    -0.08
     cough
    -0.08
     wise
    -0.08
     અંદ
    -0.08
     expertise
    -0.08
    姓名
    -0.08
    猜
    -0.08
     przypadku
    -0.07
     rythme
    -0.07
    POSITIVE LOGITS
    proc
    0.08
     zul
    0.08
     больш
    0.08
    irio
    0.08
    ulares
    0.08
     Kindle
    0.07
    uları
    0.07
     объем
    0.07
    istre
    0.07
     enorm
    0.07
    Activations Density 0.002%

    No Known Activations