© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 26519
    Prev
    Next
    INDEX
    Explanations

    民族

    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
     nucleus
    -0.08
     спис
    -0.08
     supports
    -0.07
     chassis
    -0.07
     donut
    -0.07
    matik
    -0.07
     morph
    -0.07
     injections
    -0.07
     best
    -0.07
     تث
    -0.07
    POSITIVE LOGITS
    ,实现
    0.10
     humana
    0.09
    奋斗
    0.09
    实现
    0.09
    干
    0.09
     dignity
    0.08
     الإنسانية
    0.08
     Serenity
    0.08
     البشرية
    0.08
    尊
    0.08
    Activations Density 0.001%

    No Known Activations