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. 60833
    Prev
    Next
    INDEX
    Explanations

    ---

    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
    .TYPE
    -0.08
    _ACCEPT
    -0.08
     Ayrıca
    -0.08
    ISIBLE
    -0.08
     sapat
    -0.08
    SORT
    -0.08
    _bs
    -0.07
    -des
    -0.07
    販
    -0.07
     utmost
    -0.07
    POSITIVE LOGITS
     
    0.08
    ដែល
    0.08
    First
    0.07
     
    0.07
    �
    0.07
     fers
    0.07
    ា�
    0.07
    0.07
    ✨
    0.06
    oph
    0.06
    Activations Density 0.017%

    No Known Activations