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. 11751
    Prev
    Next
    INDEX
    Explanations

    ellipses

    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
    ಕರಣ
    -0.08
     transient
    -0.08
     chante
    -0.08
     erz
    -0.08
     trick
    -0.08
     Recipient
    -0.08
    (cur
    -0.08
     hà
    -0.08
     Heimat
    -0.08
    俗
    -0.07
    POSITIVE LOGITS
     |↵↵
    0.08
    Insight
    0.08
    beg
    0.08
    Modern
    0.08
     |↵
    0.08
     appeared
    0.07
     ing
    0.07
    Insights
    0.07
    mq
    0.07
     tient
    0.07
    Activations Density 0.004%

    No Known Activations