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. 55952
    Prev
    Next
    INDEX
    Explanations

    cancer and cellular processes

    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
    评论
    -0.08
     Animated
    -0.08
     engraved
    -0.08
    -admin
    -0.07
     Pfer
    -0.07
    记录
    -0.07
    Elem
    -0.07
     dessen
    -0.07
    Recorded
    -0.07
    Moder
    -0.07
    POSITIVE LOGITS
     circumvent
    0.11
     bypass
    0.10
     evade
    0.10
     stealth
    0.10
     camouflage
    0.10
     seductive
    0.09
     infect
    0.09
    (fake
    0.09
     glam
    0.09
     takeover
    0.09
    Activations Density 0.007%

    No Known Activations