© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 8170
    Prev
    Next
    INDEX
    Explanations

    GPT models and APIs

    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
     louer
    -0.08
    спорт
    -0.08
     Amerik
    -0.08
     التجارة
    -0.08
     unlucky
    -0.08
     marít
    -0.08
     rents
    -0.08
     imóveis
    -0.08
    SELL
    -0.07
     wholes
    -0.07
    POSITIVE LOGITS
     GPT
    0.13
    GPT
    0.11
     chat
    0.10
     chatbot
    0.10
    Chat
    0.10
     bots
    0.09
    _chat
    0.09
    _ai
    0.09
    _AI
    0.09
     Chat
    0.08
    Activations Density 0.026%

    No Known Activations