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. 117458
    Prev
    Next
    INDEX
    Explanations

    a

    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
    وضح
    -0.08
     muhiim
    -0.08
    允
    -0.08
     typelib
    -0.08
     gerenciamento
    -0.08
    uvchi
    -0.08
     destructor
    -0.08
    Nm
    -0.08
     আদাল
    -0.08
     জনগ
    -0.07
    POSITIVE LOGITS
     leisurely
    0.13
     ಭೇಟಿ
    0.12
     stroll
    0.11
     bezoek
    0.11
     ಭೇಟ
    0.11
     ziyaret
    0.11
     visit
    0.11
    住宿
    0.11
     방문
    0.11
     посещ
    0.11
    Activations Density 0.187%

    No Known Activations