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. 78600
    Prev
    Next
    INDEX
    Explanations

    courage

    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
    距
    -0.08
     degr
    -0.08
     Calidad
    -0.08
    тора
    -0.08
     hut
    -0.08
     Verkehrs
    -0.08
     Klang
    -0.07
    ניה
    -0.07
     Schul
    -0.07
    odeled
    -0.07
    POSITIVE LOGITS
     courage
    0.14
     coragem
    0.14
     bravery
    0.13
     courageous
    0.12
    勇
    0.11
    fulness
    0.10
     daring
    0.10
     overcoming
    0.09
     perseverance
    0.09
     brav
    0.09
    Activations Density 0.022%

    No Known Activations