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. 53113
    Prev
    Next
    INDEX
    Explanations

    french

    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
     большое
    -0.08
     Cay
    -0.08
     Mack
    -0.08
    tas
    -0.07
     बड़ा
    -0.07
    cre
    -0.07
    CRE
    -0.07
     lane
    -0.07
     crítico
    -0.07
    anth
    -0.07
    POSITIVE LOGITS
    TPC
    0.09
     سوى
    0.09
     Riverside
    0.08
     فيها
    0.07
     лиш
    0.07
     Applicable
    0.07
     فيه
    0.07
    是假
    0.07
     Recharge
    0.07
    か
    0.07
    Activations Density 0.005%

    No Known Activations