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. 8439
    Prev
    Next
    INDEX
    Explanations

    launch and marketing online

    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
     aviation
    -0.08
    spiration
    -0.08
    chen
    -0.07
     applicability
    -0.07
     entendido
    -0.07
    提
    -0.07
     ongel
    -0.07
     конеч
    -0.07
     IBM
    -0.07
     stereotyp
    -0.07
    POSITIVE LOGITS
    Monitoring
    0.12
     monitoring
    0.11
    营销
    0.10
     campañas
    0.10
     Monitoring
    0.09
    יווק
    0.09
     regularmente
    0.09
    监
    0.09
     Outreach
    0.09
    케팅
    0.09
    Activations Density 0.014%

    No Known Activations