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. 53133
    Prev
    Next
    INDEX
    Explanations

    driving and vehicles

    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
     Convenience
    -0.08
    .mongo
    -0.07
     Hospital
    -0.07
    خصصة
    -0.07
    دارية
    -0.07
     山
    -0.07
     Jean
    -0.07
     Convenient
    -0.07
     beads
    -0.07
     fach
    -0.07
    POSITIVE LOGITS
     vigilance
    0.13
     আচ
    0.11
     поведения
    0.11
     comportements
    0.11
     vigilant
    0.11
     behaviors
    0.10
    巡视
    0.10
     courteous
    0.10
    行为
    0.10
     davran
    0.09
    Activations Density 0.015%

    No Known Activations