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. 12050
    Prev
    Next
    INDEX
    Explanations

    understanding and flexibility

    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
     inil
    -0.08
    луч
    -0.08
     mortal
    -0.08
    毎
    -0.07
     eligible
    -0.07
    ട്ര
    -0.07
     transit
    -0.07
    .kill
    -0.07
     izved
    -0.07
    глав
    -0.07
    POSITIVE LOGITS
     tolerate
    0.12
     tolerance
    0.12
     accommodating
    0.11
     forgiving
    0.11
    Tolerance
    0.11
     toler
    0.11
     allowances
    0.10
     accommodations
    0.10
     forgive
    0.10
    允许
    0.10
    Activations Density 0.055%

    No Known Activations