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. 15-RESID-POST-AA
    6. 99
    Prev
    Next
    INDEX
    Explanations

    comma

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ительным
    -0.08
    빈
    -0.08
     bénévol
    -0.07
     предлага
    -0.07
    -Ne
    -0.07
    idential
    -0.07
     این
    -0.07
     یک
    -0.07
     thick
    -0.07
    ено
    -0.07
    POSITIVE LOGITS
     glimpse
    0.10
     glance
    0.10
     glimps
    0.10
     inquiet
    0.09
     slower
    0.09
     glanced
    0.09
     olhar
    0.09
     confirmação
    0.09
     mirar
    0.09
     decreasing
    0.09
    Activations Density 0.001%

    No Known Activations