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. 77891
    Prev
    Next
    INDEX
    Explanations

    {"

    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
     yag
    -0.08
     gamme
    -0.08
     divis
    -0.07
     annonces
    -0.07
     mon
    -0.07
     erheb
    -0.07
     CALL
    -0.07
     Nederland
    -0.07
    إن
    -0.07
    CALL
    -0.07
    POSITIVE LOGITS
    	icon
    0.08
    {})
    0.07
    (icon
    0.07
    udde
    0.07
    zor
    0.07
    Developer
    0.07
    {},↵
    0.07
    	opts
    0.07
    凡
    0.07
    optimization
    0.07
    Activations Density 0.005%

    No Known Activations