Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 77344
    Prev
    Next
    INDEX
    Explanations

    instructions and spanish fragments

    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
    |null
    -0.08
    轻
    -0.08
    DS
    -0.08
    (normal
    -0.08
    次
    -0.07
    监
    -0.07
    /check
    -0.07
     haf
    -0.07
     SITE
    -0.07
    虹
    -0.07
    POSITIVE LOGITS
     streamlined
    0.15
     efficient
    0.13
     concise
    0.12
    efficient
    0.12
     effiz
    0.12
    focused
    0.11
     effizient
    0.11
    -efficient
    0.11
     economical
    0.11
    効
    0.11
    Activations Density 0.082%

    No Known Activations