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. 113037
    Prev
    Next
    INDEX
    Explanations

    canopy

    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
     Stein
    -0.09
    inston
    -0.08
    කි
    -0.07
     instantiate
    -0.07
    CRC
    -0.07
     измер
    -0.07
     mess
    -0.07
     nand
    -0.07
    ürk
    -0.07
    176
    -0.07
    POSITIVE LOGITS
     canopy
    0.10
    航
    0.09
     Betr
    0.08
    罩
    0.08
     bawah
    0.08
    ထ
    0.08
    圈
    0.08
     jeune
    0.08
    iast
    0.08
     ထ
    0.08
    Activations Density 0.001%

    No Known Activations