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. 12688
    Prev
    Next
    INDEX
    Explanations

    code, Jinja

    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
    implant
    -0.10
     Princeton
    -0.08
    _PACKET
    -0.08
    ching
    -0.08
    acency
    -0.08
     IPO
    -0.08
     سرطان
    -0.08
    Philadelphia
    -0.07
     организм
    -0.07
    Drive
    -0.07
    POSITIVE LOGITS
     Twig
    0.10
     Bean
    0.09
     bean
    0.09
     }}↵
    0.08
    Twig
    0.08
    bean
    0.08
     sass
    0.08
    "}}
    0.08
     }}↵↵
    0.08
    Bean
    0.08
    Activations Density 0.007%

    No Known Activations