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. 59342
    Prev
    Next
    INDEX
    Explanations

    略

    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
     Cheryl
    -0.09
     ooit
    -0.08
     Nikki
    -0.08
    458
    -0.08
     നൽകി
    -0.08
     foolish
    -0.08
     invaluable
    -0.07
    Lamp
    -0.07
     Bernard
    -0.07
     exalt
    -0.07
    POSITIVE LOGITS
    有所
    0.15
     vary
    0.15
     differ
    0.14
     تختلف
    0.14
     variar
    0.13
     varier
    0.13
     differs
    0.13
     متفاوت
    0.13
     berbeda
    0.12
     varied
    0.12
    Activations Density 0.024%

    No Known Activations