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. 23959
    Prev
    Next
    INDEX
    Explanations

    first

    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
    culated
    -0.08
    atoria
    -0.08
    stories
    -0.08
     hardships
    -0.07
     실패
    -0.07
    osomes
    -0.07
    retanto
    -0.07
    nde
    -0.07
    인을
    -0.07
    claimed
    -0.07
    POSITIVE LOGITS
    WELCOME
    0.09
    Perg
    0.09
    詢
    0.08
     welcoming
    0.08
     Yem
    0.08
     Hampshire
    0.08
     perguntas
    0.08
     приглаш
    0.08
     pergunta
    0.08
    Pregunta
    0.08
    Activations Density 0.006%

    No Known Activations