Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 75884
    Prev
    Next
    INDEX
    Explanations

    heat

    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
     serene
    -0.08
     copyrights
    -0.08
     calma
    -0.07
     ontspannen
    -0.07
    bags
    -0.07
     flexibel
    -0.07
    ENDAR
    -0.07
     يرج
    -0.07
    لين
    -0.07
     Ved
    -0.07
    POSITIVE LOGITS
     aggressively
    0.09
    -fast
    0.09
     hızlı
    0.09
     vitesse
    0.09
     aggressive
    0.09
     سریع
    0.09
     سرعت
    0.09
    猛
    0.09
     agres
    0.09
     agress
    0.09
    Activations Density 0.007%

    No Known Activations