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. 88229
    Prev
    Next
    INDEX
    Explanations

    Drug

    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
    -0.08
    。”
    -0.08
     parms
    -0.08
     คู่
    -0.08
    Livre
    -0.08
     Vold
    -0.08
    。”↵↵
    -0.07
    。)
    -0.07
     critica
    -0.07
    ราะ
    -0.07
    POSITIVE LOGITS
    &nbsp
    0.08
     set
    0.07
     sedent
    0.07
    Paragraph
    0.07
    ऱ
    0.07
     поход
    0.07
    കാര്യ
    0.07
    -occ
    0.07
    [left
    0.07
    k
    0.07
    Activations Density 0.245%

    No Known Activations