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. 43729
    Prev
    Next
    INDEX
    Explanations

    Citations with page numbers

    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
    osing
    -0.08
     yönelik
    -0.08
    lose
    -0.08
    Routing
    -0.08
    Validators
    -0.07
    nent
    -0.07
    -function
    -0.07
    Restriction
    -0.07
    Made
    -0.07
    (holder
    -0.07
    POSITIVE LOGITS
     উদ্ধ
    0.11
    章节
    0.11
    引用
    0.10
     excerpts
    0.10
     cites
    0.10
     cite
    0.09
     chapter
    0.09
     Chapter
    0.09
     capítulos
    0.09
     Cite
    0.09
    Activations Density 0.007%

    No Known Activations