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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 49624
    Prev
    Next
    INDEX
    Explanations

    wag

    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
     아니라
    -0.08
     supervisor
    -0.08
    /sidebar
    -0.08
    uters
    -0.08
     SAT
    -0.08
     물론
    -0.08
     skeptical
    -0.08
    .segment
    -0.08
     전
    -0.08
    UA
    -0.08
    POSITIVE LOGITS
    Finance
    0.08
    finance
    0.07
    తో
    0.07
    ман
    0.07
     Geld
    0.07
    ిచ
    0.07
    壮
    0.07
    :"#
    0.07
     OUTPUT
    0.07
     FIN
    0.07
    Activations Density 0.003%

    No Known Activations