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. 56148
    Prev
    Next
    INDEX
    Explanations

    X-men

    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
     cookware
    -0.09
     triglycer
    -0.09
     bsp
    -0.08
     Ware
    -0.08
    ivaa
    -0.08
     backlink
    -0.08
     Cine
    -0.08
    ով
    -0.08
     एयर
    -0.07
     ایرانی
    -0.07
    POSITIVE LOGITS
     provoc
    0.08
     debat
    0.08
    Observable
    0.08
     mutated
    0.08
     буду
    0.08
     disabilities
    0.08
     IOException
    0.07
    GV
    0.07
    (Collections
    0.07
    .props
    0.07
    Activations Density 0.005%

    No Known Activations