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. 67432
    Prev
    Next
    INDEX
    Explanations

    name etymology

    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
     anne
    -0.08
     Anne
    -0.08
    ænd
    -0.07
    Anne
    -0.07
     есть
    -0.07
     Craig
    -0.07
    prek
    -0.07
     revamped
    -0.07
     dropping
    -0.07
    prepare
    -0.07
    POSITIVE LOGITS
    ortu
    0.09
    sic
    0.09
     verlang
    0.08
    attan
    0.08
    abilidad
    0.08
    ianza
    0.08
     حاول
    0.08
    ORT
    0.08
     {},↵
    0.08
     تبحث
    0.08
    Activations Density 0.054%

    No Known Activations