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. 45946
    Prev
    Next
    INDEX
    Explanations

    view

    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
     landet
    -0.08
     взрос
    -0.08
     sobe
    -0.08
    Landing
    -0.07
     indent
    -0.07
     sil
    -0.07
    ________________
    -0.07
     sounded
    -0.07
     __________________
    -0.07
     leuc
    -0.07
    POSITIVE LOGITS
    Cars
    0.08
     Shoes
    0.08
    体彩
    0.08
    .Mesh
    0.08
    ometri
    0.08
     Inspirations
    0.07
     coping
    0.07
     Extremely
    0.07
     parade
    0.07
    中文字
    0.07
    Activations Density 0.001%

    No Known Activations