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. 104022
    Prev
    Next
    INDEX
    Explanations

    support

    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
     Consult
    -0.08
     mañana
    -0.08
    교
    -0.08
    ையே
    -0.07
     الحجر
    -0.07
     Beratung
    -0.07
    ம்ம
    -0.07
    school
    -0.07
     एक्स
    -0.07
     Nowadays
    -0.07
    POSITIVE LOGITS
    力度
    0.10
     soutenir
    0.10
     envers
    0.10
     støtte
    0.10
     soutien
    0.10
    /support
    0.08
    支持
    0.08
     terhadap
    0.08
     sentiments
    0.08
    ต่
    0.08
    Activations Density 0.057%

    No Known Activations