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

    Neuronpedia

    APICircuit 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. 88272
    Prev
    Next
    INDEX
    Explanations

    define

    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
     houding
    -0.09
     모르
    -0.08
    Zend
    -0.08
    Compose
    -0.08
    dlg
    -0.08
    DNS
    -0.08
    nej
    -0.08
    Бу
    -0.07
    Mehr
    -0.07
    Uber
    -0.07
    POSITIVE LOGITS
    #define
    0.08
    'ed
    0.08
    ihl
    0.08
     �
    0.07
     sand
    0.07
     Elliott
    0.07
     """↵↵
    0.07
     округ
    0.07
     Soldier
    0.07
     datap
    0.07
    Activations Density 0.002%

    No Known Activations