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. 90083
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
     Lizenz
    -0.09
     lacus
    -0.08
     gravid
    -0.08
     laying
    -0.08
     anche
    -0.08
     Côte
    -0.08
    ીના
    -0.07
     ซึ่ง
    -0.07
     USA
    -0.07
     รุ่น
    -0.07
    POSITIVE LOGITS
     fails
    0.11
     failure
    0.10
    Failure
    0.09
     failed
    0.09
    Failed
    0.09
     olmadığı
    0.08
     normally
    0.08
    Excluded
    0.08
     dt
    0.08
    fails
    0.08
    Activations Density 0.077%

    No Known Activations