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. 55729
    Prev
    Next
    INDEX
    Explanations

    SL

    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
     accueill
    -0.09
     ಗೊ
    -0.08
     vastaan
    -0.08
    rokken
    -0.08
     vår
    -0.08
     gegenüber
    -0.08
    hore
    -0.08
     ಎ
    -0.08
    Reception
    -0.07
     ಉ
    -0.07
    POSITIVE LOGITS
     conduction
    0.08
     lack
    0.08
     efficiency
    0.07
    unak
    0.07
    Mana
    0.07
     effort
    0.07
     underestimated
    0.07
    .mem
    0.07
     mutually
    0.07
     Dana
    0.07
    Activations Density 0.000%

    No Known Activations