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. 11-RESID-POST-AA
    6. 78334
    Prev
    Next
    INDEX
    Explanations

    portable

    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
    ùng
    -0.08
    沿
    -0.07
     watered
    -0.07
    áci
    -0.07
    小学
    -0.07
    Reduction
    -0.07
     inplace
    -0.07
    堂
    -0.07
    ambil
    -0.07
     обще
    -0.07
    POSITIVE LOGITS
     Altern
    0.08
    _datas
    0.08
    ongan
    0.08
     ما
    0.07
     incr
    0.07
    folio
    0.07
     Zot
    0.07
    _exec
    0.07
    ibilidad
    0.07
     Cold
    0.07
    Activations Density 0.005%

    No Known Activations