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. 30771
    Prev
    Next
    INDEX
    Explanations

    names

    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
    Humidity
    -0.09
    	category
    -0.09
     ја
    -0.09
    	volatile
    -0.09
     Derecho
    -0.09
     humidity
    -0.08
    	DECLARE
    -0.08
    	CHECK
    -0.08
     THANK
    -0.08
    humidity
    -0.08
    POSITIVE LOGITS
    _generic
    0.09
     নামে
    0.09
    -n
    0.08
     spelled
    0.08
    义
    0.08
    姓
    0.07
     generic
    0.07
    名字
    0.07
     name
    0.07
     universally
    0.07
    Activations Density 0.090%

    No Known Activations