© 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. 47920
    Prev
    Next
    INDEX
    Explanations

    Firebase configuration

    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
     produc
    -0.08
     presyo
    -0.08
     dobl
    -0.08
     prezzo
    -0.08
     પૈ
    -0.08
     цена
    -0.07
     Harga
    -0.07
    -upper
    -0.07
     гум
    -0.07
     נס
    -0.07
    POSITIVE LOGITS
     initialization
    0.12
    configure
    0.11
    .configure
    0.11
     configured
    0.11
     Configure
    0.11
     configure
    0.10
    配置
    0.10
    Configure
    0.10
    Configured
    0.10
    configured
    0.10
    Activations Density 0.004%

    No Known Activations