© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 8167
    Prev
    Next
    INDEX
    Explanations

    mask

    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
     Theodore
    -0.08
     Dad
    -0.08
    -dev
    -0.08
     fara
    -0.08
    ೆಗೆ
    -0.07
     niches
    -0.07
     equipment
    -0.07
    _DEV
    -0.07
    entwick
    -0.07
    ξης
    -0.07
    POSITIVE LOGITS
    itoare
    0.09
    .astype
    0.08
     rectangular
    0.08
     enforcing
    0.08
     imposto
    0.07
    RIS
    0.07
     imp
    0.07
     भ्रष्ट
    0.07
     sév
    0.07
     tougher
    0.07
    Activations Density 0.001%

    No Known Activations