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. 19663
    Prev
    Next
    INDEX
    Explanations

    辞

    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
    .call
    -0.09
     فرا
    -0.08
    -0.08
     Māori
    -0.08
    .cached
    -0.08
     آمد
    -0.08
    /USD
    -0.08
    ாவது
    -0.07
     தீ
    -0.07
    .Hash
    -0.07
    POSITIVE LOGITS
    —all
    0.10
     privile
    0.10
     privil
    0.09
     altogether
    0.08
    -letter
    0.08
     sorti
    0.08
    glied
    0.08
     weder
    0.08
     bâtiment
    0.08
     ((((
    0.07
    Activations Density 0.004%

    No Known Activations