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. 53448
    Prev
    Next
    INDEX
    Explanations

    td

    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
     determinant
    -0.08
     keuzes
    -0.07
     usernames
    -0.07
    chosen
    -0.07
    -0.07
    纪录
    -0.07
     disrespect
    -0.07
     записи
    -0.07
    破
    -0.07
     detector
    -0.07
    POSITIVE LOGITS
     कृषि
    0.08
    Markets
    0.08
    ARY
    0.08
     fertile
    0.08
     rowspan
    0.08
     balón
    0.08
     relaxed
    0.07
    .Child
    0.07
     साइ
    0.07
    วิ
    0.07
    Activations Density 0.002%

    No Known Activations