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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 49153
    Prev
    Next
    INDEX
    Explanations

    lower and upper bounds

    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
     життя
    -0.08
     revital
    -0.08
    が
    -0.08
    如
    -0.07
    例如
    -0.07
    刑
    -0.07
    丝
    -0.07
    ਿਆਂ
    -0.07
    絲
    -0.07
    萬元
    -0.07
    POSITIVE LOGITS
    _seek
    0.08
     predecess
    0.08
     찾
    0.08
     seeker
    0.08
    closest
    0.08
     Europeans
    0.08
     maximal
    0.08
    Closest
    0.08
     floor
    0.08
     Searching
    0.08
    Activations Density 0.007%

    No Known Activations