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. 9050
    Prev
    Next
    INDEX
    Explanations

    a

    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
    BERS
    -0.09
     المنظمة
    -0.08
    legi
    -0.08
    天下
    -0.08
     gotten
    -0.08
     مطرح
    -0.08
     endorsed
    -0.08
    கர்
    -0.07
    sup
    -0.07
     potent
    -0.07
    POSITIVE LOGITS
    柔
    0.07
     foto
    0.07
    Warm
    0.07
    色
    0.07
     rojo
    0.07
     Positioned
    0.07
     profundidad
    0.07
    iano
    0.07
    0.07
     bestuur
    0.07
    Activations Density 0.005%

    No Known Activations