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. 58686
    Prev
    Next
    INDEX
    Explanations

    tolerate

    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
    邀请
    -0.09
    <nav
    -0.09
    影
    -0.08
     okwu
    -0.08
    影视
    -0.08
     оформ
    -0.08
    ולם
    -0.08
     invite
    -0.08
     allegation
    -0.07
    _choices
    -0.07
    POSITIVE LOGITS
     tolerant
    0.12
     hardy
    0.11
     toler
    0.11
     tolerate
    0.11
     tolerance
    0.10
     resilience
    0.10
     adaptability
    0.09
    Tolerance
    0.09
     drought
    0.09
     resilient
    0.08
    Activations Density 0.019%

    No Known Activations