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. 65167
    Prev
    Next
    INDEX
    Explanations

    from

    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
     гриб
    -0.10
    ратите
    -0.09
     عمان
    -0.08
     आतंक
    -0.08
     अभ्यास
    -0.08
    ․․
    -0.08
     приступ
    -0.08
     ант
    -0.08
     تجد
    -0.08
     പുതിയ
    -0.08
    POSITIVE LOGITS
     bound
    0.08
     musical
    0.08
    ound
    0.08
    _bind
    0.08
     betray
    0.07
    obox
    0.07
    Dex
    0.07
     musicals
    0.07
     형
    0.07
     defe
    0.07
    Activations Density 0.001%

    No Known Activations