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. 44046
    Prev
    Next
    INDEX
    Explanations

    keywords

    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
    幸福
    -0.08
     uppsk
    -0.08
     lavish
    -0.08
     kry
    -0.08
    wam
    -0.08
    _pcm
    -0.07
     wam
    -0.07
     willingness
    -0.07
     scratch
    -0.07
     príncipe
    -0.07
    POSITIVE LOGITS
    keywords
    0.11
     Keywords
    0.10
     Keyword
    0.10
    (keyword
    0.10
     keywords
    0.10
     Reserved
    0.09
    .Keyword
    0.09
    keyword
    0.09
     keyword
    0.09
     reserved
    0.09
    Activations Density 0.003%

    No Known Activations