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. 106052
    Prev
    Next
    INDEX
    Explanations

    arp

    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
     nearby
    -0.09
     Nearby
    -0.07
     LU
    -0.07
     ഒരു
    -0.07
     rara
    -0.07
     GG
    -0.07
     DK
    -0.07
     xüsusi
    -0.07
     Parma
    -0.07
     DIY
    -0.07
    POSITIVE LOGITS
     pait
    0.09
    ொண்ட
    0.09
     пищ
    0.09
    .truth
    0.08
     বিজ
    0.08
    贯彻
    0.08
    bije
    0.08
    	map
    0.08
    服务器
    0.08
    ()==
    0.08
    Activations Density 0.000%

    No Known Activations