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. 48189
    Prev
    Next
    INDEX
    Explanations

    followed

    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
     optimum
    -0.08
     Kale
    -0.08
     Fuj
    -0.07
     Serr
    -0.07
    общ
    -0.07
     sas
    -0.07
    别人
    -0.07
    operation
    -0.07
    .sale
    -0.07
     samengesteld
    -0.07
    POSITIVE LOGITS
    อย่าง
    0.08
    スク
    0.08
    การ
    0.08
     lavish
    0.08
    ゃ
    0.07
     ई
    0.07
     सकता
    0.07
     সংশ
    0.07
     Explanation
    0.07
    スタ
    0.07
    Activations Density 0.029%

    No Known Activations