Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 88074
    Prev
    Next
    INDEX
    Explanations

    delay

    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
    Delayed
    -0.09
    暂停
    -0.09
    	sleep
    -0.09
    	timeout
    -0.08
     sinc
    -0.08
    延期
    -0.08
    	wait
    -0.08
    .wait
    -0.08
    sleep
    -0.08
     sleep
    -0.08
    POSITIVE LOGITS
    ogat
    0.08
     erop
    0.08
     geprägt
    0.08
    .view
    0.08
    句
    0.07
     Latin
    0.07
    ేని
    0.07
    íticas
    0.07
    Edu
    0.07
    restaurant
    0.07
    Activations Density 0.001%

    No Known Activations