Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 19025
    Prev
    Next
    INDEX
    Explanations

    for

    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
    ‌ను
    -0.08
     ను
    -0.08
    :
    -0.08
    /name
    -0.08
    Woman
    -0.07
    ‌లో
    -0.07
    Tall
    -0.07
    .Storage
    -0.07
    Aura
    -0.07
    _W
    -0.07
    POSITIVE LOGITS
     미래
    0.11
     zukünft
    0.11
    ,也是
    0.10
     future
    0.10
     будущ
    0.10
     futuras
    0.10
     geworden
    0.10
     اصلی
    0.10
     الأحداث
    0.10
    未来
    0.10
    Activations Density 0.036%

    No Known Activations