Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 12101
    Prev
    Next
    INDEX
    Explanations

    speculative computer architecture

    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
     attention
    -0.08
     beh
    -0.07
     exposure
    -0.07
     baño
    -0.07
     perhatian
    -0.07
     bloot
    -0.07
     expose
    -0.07
     times
    -0.07
     exposed
    -0.07
    敦
    -0.07
    POSITIVE LOGITS
     guesses
    0.13
     guess
    0.13
    guess
    0.13
    预测
    0.12
     speculative
    0.12
     guessed
    0.12
    _guess
    0.12
    猜
    0.12
     अनुमान
    0.12
     уга
    0.11
    Activations Density 0.004%

    No Known Activations