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. 114031
    Prev
    Next
    INDEX
    Explanations

    on

    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
     murals
    -0.09
     Visits
    -0.09
     celebrations
    -0.09
     Ventures
    -0.08
    _visit
    -0.08
     घटन
    -0.08
    사회
    -0.08
     visitation
    -0.08
     Prison
    -0.08
     Crimes
    -0.08
    POSITIVE LOGITS
    型号
    0.16
     Samsung
    0.14
     Lenovo
    0.14
    Samsung
    0.13
    購入
    0.13
     ASUS
    0.13
     కొన
    0.13
    购买
    0.13
     ખરી
    0.13
     purchased
    0.13
    Activations Density 0.277%

    No Known Activations