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. 119354
    Prev
    Next
    INDEX
    Explanations

    top

    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
    .struct
    -0.08
    들은
    -0.07
     पक्ष
    -0.07
     qon
    -0.07
    .codes
    -0.07
    struct
    -0.07
    conn
    -0.07
     индивиду
    -0.07
     conn
    -0.07
    Note
    -0.07
    POSITIVE LOGITS
    忆
    0.10
     వేస
    0.09
    顶部
    0.09
    nofollow
    0.09
     удоб
    0.08
     ফিরে
    0.08
     obrá
    0.08
     vuelve
    0.08
    абы
    0.08
    helves
    0.08
    Activations Density 0.002%

    No Known Activations