© 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
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 30128
    Prev
    Next
    INDEX
    Explanations

    see/we

    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
     liebsten
    -0.08
    useum
    -0.08
    하는
    -0.07
    .average
    -0.07
    urge
    -0.07
     کردن
    -0.07
     nursing
    -0.07
    .Response
    -0.07
     ನಾಗ
    -0.07
     મ
    -0.07
    POSITIVE LOGITS
     দেখা
    0.08
     أنها
    0.08
     أنه
    0.08
    ట్టి
    0.07
     видно
    0.07
     tensions
    0.07
     gef
    0.07
     দেখি
    0.07
    иат
    0.07
    	It
    0.07
    Activations Density 0.030%

    No Known Activations