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. 58852
    Prev
    Next
    INDEX
    Explanations

    hyphens

    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
    izy
    -0.08
     domin
    -0.07
     在
    -0.07
     Mog
    -0.07
    m
    -0.07
     ต่
    -0.07
     magnets
    -0.07
    /forum
    -0.07
     rota
    -0.07
    licken
    -0.07
    POSITIVE LOGITS
    pere
    0.08
     안
    0.08
    capture
    0.07
    /UI
    0.07
     Savage
    0.07
     childhood
    0.07
     ken
    0.07
    ably
    0.07
    ован
    0.07
     ECG
    0.07
    Activations Density 0.003%

    No Known Activations