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. 75890
    Prev
    Next
    INDEX
    Explanations

    Code libraries and snippets

    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
     दूस
    -0.09
     _______,
    -0.09
     hungry
    -0.09
     mindful
    -0.08
    (dto
    -0.08
     וג
    -0.08
     noticeable
    -0.08
     affluent
    -0.08
     похудения
    -0.08
    .Te
    -0.08
    POSITIVE LOGITS
    .class
    0.09
     functionalities
    0.08
     semantic
    0.08
     protocol
    0.08
     suite
    0.07
     functionality
    0.07
     Container
    0.07
    Quartz
    0.07
    RFC
    0.07
    Protocol
    0.07
    Activations Density 0.057%

    No Known Activations