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. 43626
    Prev
    Next
    INDEX
    Explanations

    PTFE

    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
     tall
    -0.08
    алин
    -0.08
    648
    -0.08
    cen
    -0.07
     qəbul
    -0.07
    огор
    -0.07
    стр
    -0.07
     ace
    -0.07
    qr
    -0.07
    уст
    -0.07
    POSITIVE LOGITS
    Muh
    0.09
    �
    0.09
    ®
    0.08
    -coated
    0.08
    Pizza
    0.08
    Hovered
    0.08
     membr
    0.08
    漂
    0.07
     pizzas
    0.07
    oka
    0.07
    Activations Density 0.002%

    No Known Activations