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. 65681
    Prev
    Next
    INDEX
    Explanations

    Shirts and art

    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
     transformers
    -0.08
     अर्ज
    -0.07
     बात
    -0.07
     Carpenter
    -0.07
    रो
    -0.07
     मेहन
    -0.07
     arac
    -0.07
    ással
    -0.07
    Adi
    -0.07
    Dan
    -0.07
    POSITIVE LOGITS
     ના
    0.07
     우
    0.07
     સે
    0.07
    iks
    0.07
     Ka
    0.07
     كذلك
    0.07
     geil
    0.07
     antiguo
    0.07
    keypress
    0.07
     keren
    0.07
    Activations Density 0.013%

    No Known Activations