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. 55823
    Prev
    Next
    INDEX
    Explanations

    letter

    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
     cement
    -0.07
     начин
    -0.07
    ים
    -0.07
     anten
    -0.07
     UFO
    -0.07
     ов
    -0.07
    fund
    -0.07
     Christoph
    -0.07
    oland
    -0.07
     oscill
    -0.07
    POSITIVE LOGITS
     ngosi
    0.09
    acters
    0.08
    -chave
    0.08
     그대로
    0.08
     камп
    0.08
    innen
    0.08
     dioxide
    0.08
     Vir
    0.08
    BRE
    0.08
     gymnastics
    0.08
    Activations Density 0.014%

    No Known Activations