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. 12796
    Prev
    Next
    INDEX
    Explanations

    have

    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
     ث
    -0.08
     गेल
    -0.08
     tính
    -0.08
     leto
    -0.07
     enforced
    -0.07
     Gelen
    -0.07
    بيع
    -0.07
     بحران
    -0.07
    $current
    -0.07
     enforcement
    -0.07
    POSITIVE LOGITS
    桃
    0.08
    姓
    0.08
    veh
    0.08
    客様
    0.07
    _utf
    0.07
    mongodb
    0.07
    ókn
    0.07
    ictured
    0.07
    25
    0.07
    Vertical
    0.07
    Activations Density 0.001%

    No Known Activations