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. 53164
    Prev
    Next
    INDEX
    Explanations

    equals sign

    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
    رف
    -0.08
    统
    -0.08
     rigtig
    -0.07
     nhất
    -0.07
     historical
    -0.07
    RC
    -0.07
    Ord
    -0.07
    xea
    -0.07
    ുമായ
    -0.07
    ിൻ
    -0.07
    POSITIVE LOGITS
     voila
    0.11
     Ainsi
    0.08
    unkte
    0.08
    ylan
    0.08
    Ainsi
    0.08
     பெற்ற
    0.08
     voilà
    0.08
     Таким
    0.08
    (or
    0.07
    �
    0.07
    Activations Density 0.081%

    No Known Activations