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. 12852
    Prev
    Next
    INDEX
    Explanations

    不能

    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
     那
    -0.09
     �
    -0.08
     STD
    -0.08
     �
    -0.08
    看看
    -0.08
     cod
    -0.08
     cows
    -0.08
    ្មី
    -0.08
     Schauspiel
    -0.08
     美
    -0.08
    POSITIVE LOGITS
     prohibition
    0.09
    は禁止
    0.09
     лиш
    0.09
     запрещ
    0.09
     prohibited
    0.08
     dürfen
    0.08
    oni
    0.08
     relentlessly
    0.08
    excluded
    0.08
     darf
    0.08
    Activations Density 0.001%

    No Known Activations