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. 59757
    Prev
    Next
    INDEX
    Explanations

    way

    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
     chambers
    -0.08
     Klein
    -0.08
     vir
    -0.07
     kal
    -0.07
     Sea
    -0.07
    _helpers
    -0.07
     cav
    -0.07
     ACC
    -0.07
    sharp
    -0.07
     Кал
    -0.07
    POSITIVE LOGITS
     Pf
    0.10
    fully
    0.08
     Davis
    0.08
    索
    0.08
     hidup
    0.07
     dictated
    0.07
    CID
    0.07
     Winters
    0.07
    ologies
    0.07
    finder
    0.07
    Activations Density 0.065%

    No Known Activations