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. 43118
    Prev
    Next
    INDEX
    Explanations

    conversational

    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
    /her
    -0.09
     τί
    -0.08
     மேல
    -0.07
     lions
    -0.07
    -0.07
     Apples
    -0.07
     מידע
    -0.07
    ’re
    -0.07
     συγκεκρι
    -0.07
     δεί
    -0.07
    POSITIVE LOGITS
    izable
    0.08
    .Bot
    0.08
    型
    0.08
    FAB
    0.08
    ्यता
    0.08
    HK
    0.08
     maintenance
    0.08
    ية
    0.08
    .Condition
    0.08
     pacing
    0.08
    Activations Density 0.003%

    No Known Activations