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. 53907
    Prev
    Next
    INDEX
    Explanations

    notice, paying attention

    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
     Bru
    -0.10
     હોય
    -0.08
    认为
    -0.08
    ಿಗ
    -0.08
    ]=
    -0.08
     Certainly
    -0.08
    یکار
    -0.08
     બની
    -0.08
    ariat
    -0.07
     prze
    -0.07
    POSITIVE LOGITS
     subtly
    0.09
    Notice
    0.08
     hierbei
    0.08
     subtle
    0.08
     gap
    0.08
    оғ
    0.08
     distin
    0.08
     queijo
    0.08
    这里
    0.08
    ESH
    0.08
    Activations Density 0.028%

    No Known Activations