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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 42928
    Prev
    Next
    INDEX
    Explanations

    opus

    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
    atched
    -0.09
    igheter
    -0.08
    (engine
    -0.08
     Jeremy
    -0.08
     अपे
    -0.08
     medd
    -0.08
     वितरण
    -0.08
    .driver
    -0.08
    posting
    -0.08
     वित
    -0.07
    POSITIVE LOGITS
    ®
    0.09
    ®,
    0.09
    ®.
    0.09
     �
    0.08
     Uni
    0.08
     halal
    0.08
     ainsi
    0.07
     ®
    0.07
    쇼
    0.07
    ഹ
    0.07
    Activations Density 0.143%

    No Known Activations