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

    Neuronpedia

    APICircuit 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. 53986
    Prev
    Next
    INDEX
    Explanations

    Real-time operating systems

    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
    默
    -0.08
    	auto
    -0.07
    Bon
    -0.07
     randomly
    -0.07
     nostalgic
    -0.07
    	m
    -0.07
    Leon
    -0.07
    __.
    -0.07
     Serie
    -0.07
     постеп
    -0.07
    POSITIVE LOGITS
     printk
    0.10
    irq
    0.10
     IRQ
    0.09
    _irq
    0.09
    _IRQ
    0.09
    _interrupt
    0.09
     Interrupt
    0.09
     OSX
    0.09
     uptime
    0.09
     irq
    0.09
    Activations Density 0.005%

    No Known Activations