© 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. 29674
    Prev
    Next
    INDEX
    Explanations

    diffuser, user

    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
    रिक
    -0.08
     prompting
    -0.07
     osjeć
    -0.07
     generation
    -0.07
     निर्म
    -0.07
     रिक
    -0.07
    finding
    -0.07
    memor
    -0.07
     centimeter
    -0.07
    etre
    -0.07
    POSITIVE LOGITS
     яг
    0.08
    Colours
    0.08
    .Settings
    0.08
     Magnum
    0.07
    	Logger
    0.07
    IMPLE
    0.07
    York
    0.07
     Logger
    0.07
     York
    0.07
     Executes
    0.07
    Activations Density 0.001%

    No Known Activations