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. 78662
    Prev
    Next
    INDEX
    Explanations

    side

    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
    zug
    -0.08
     Flint
    -0.08
    集团
    -0.08
    旗下
    -0.07
    gev
    -0.07
    edi
    -0.07
     Glue
    -0.07
     linh
    -0.07
     central
    -0.07
    ชุด
    -0.07
    POSITIVE LOGITS
     закреп
    0.08
    さい
    0.08
     الأقل
    0.08
     Thorough
    0.08
     cuidadosamente
    0.08
     మార్చ
    0.08
     thoroughly
    0.07
     السعودية
    0.07
    .ASC
    0.07
     Un
    0.07
    Activations Density 0.002%

    No Known Activations