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. 78645
    Prev
    Next
    INDEX
    Explanations

    dare

    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
    atig
    -0.09
    pons
    -0.09
     коль
    -0.08
     ворот
    -0.08
    capitalize
    -0.08
    lacht
    -0.08
    .Level
    -0.08
    .SIZE
    -0.08
    veer
    -0.08
     latch
    -0.08
    POSITIVE LOGITS
     دید
    0.09
     شئ
    0.09
    عدم
    0.07
     ಸಾಮಾಜಿಕ
    0.07
     social
    0.07
    以后
    0.07
     estando
    0.07
     dood
    0.07
     Turkish
    0.07
    ห
    0.07
    Activations Density 0.000%

    No Known Activations