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. 30194
    Prev
    Next
    INDEX
    Explanations

    sqrt

    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
     repayment
    -0.08
     Completion
    -0.08
     repetitions
    -0.08
     surcharge
    -0.08
    completion
    -0.08
    优
    -0.08
     пора
    -0.07
     embr
    -0.07
    優
    -0.07
    /com
    -0.07
    POSITIVE LOGITS
     rozd
    0.09
    .diff
    0.09
    ಿಮಾನ
    0.08
    .doc
    0.08
    .stdout
    0.08
    աւ
    0.08
     없이
    0.07
    Diff
    0.07
     befest
    0.07
    Doc
    0.07
    Activations Density 0.011%

    No Known Activations