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. 45316
    Prev
    Next
    INDEX
    Explanations

    running and walking

    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
     oferecer
    -0.09
     പോല
    -0.08
    Subscribers
    -0.08
     св
    -0.08
    Prest
    -0.08
    zap
    -0.08
    moon
    -0.08
     גדולה
    -0.08
    ിയിലെ
    -0.08
     nabíd
    -0.08
    POSITIVE LOGITS
    途中
    0.11
     cuesta
    0.10
     uphill
    0.08
     Waik
    0.08
    Away
    0.08
     away
    0.08
     Away
    0.08
     proportional
    0.08
     paths
    0.08
     southeast
    0.08
    Activations Density 0.019%

    No Known Activations