© 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. 108649
    Prev
    Next
    INDEX
    Explanations

    image generation prompts

    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
     racional
    -0.09
    ZR
    -0.08
     الموقع
    -0.08
     اتخاذ
    -0.08
     rational
    -0.08
    gründ
    -0.08
     jamb
    -0.07
     Rational
    -0.07
     سازی
    -0.07
     توقع
    -0.07
    POSITIVE LOGITS
     swimming
    0.14
     swim
    0.14
     swims
    0.13
     Swimming
    0.12
     coral
    0.11
     submarine
    0.11
     Swim
    0.11
     buoy
    0.11
     algae
    0.11
     underwater
    0.10
    Activations Density 0.048%

    No Known Activations