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. 109508
    Prev
    Next
    INDEX
    Explanations

    captured

    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
     bzw
    -0.08
     Wonderful
    -0.08
     coses
    -0.08
     Hoa
    -0.07
    [Index
    -0.07
    Uvs
    -0.07
     filles
    -0.07
    Updates
    -0.07
     Duk
    -0.07
     bizi
    -0.07
    POSITIVE LOGITS
     mastering
    0.08
     shot
    0.08
     chilling
    0.08
     vividly
    0.08
    抓
    0.08
    464
    0.08
    打造
    0.08
     словно
    0.07
     손
    0.07
     �
    0.07
    Activations Density 0.004%

    No Known Activations