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. 120339
    Prev
    Next
    INDEX
    Explanations

    smart contract access control

    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
     København
    -0.07
    IMS
    -0.07
     అనంత
    -0.07
    ISTICS
    -0.07
     revista
    -0.07
    vit
    -0.07
    adol
    -0.07
    訂
    -0.07
    全年
    -0.07
    stre
    -0.07
    POSITIVE LOGITS
     authorized
    0.12
     unauthorized
    0.12
     rightful
    0.10
    authorized
    0.10
     누구
    0.10
     autorizado
    0.10
     authorize
    0.10
     autorização
    0.10
    Authorized
    0.10
     Authorized
    0.10
    Activations Density 0.003%

    No Known Activations