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. 112591
    Prev
    Next
    INDEX
    Explanations

    code, documentation, multiple languages

    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
    Su
    -0.08
     Quil
    -0.08
    Me
    -0.07
    Define
    -0.07
     jeweils
    -0.07
    Paragraph
    -0.07
    Adding
    -0.07
    Cro
    -0.07
    ---↵↵
    -0.07
    sar
    -0.07
    POSITIVE LOGITS
    大的
    0.09
     MAS
    0.08
     hotter
    0.08
    快三
    0.08
     elongated
    0.08
     magas
    0.08
    حول
    0.08
    不过
    0.08
     낮
    0.08
     slower
    0.08
    Activations Density 0.030%

    No Known Activations