© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 44840
    Prev
    Next
    INDEX
    Explanations

    developer mode

    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
    Estimate
    -0.08
    _LOCK
    -0.08
    Transfer
    -0.07
     Estimate
    -0.07
    由
    -0.07
    ブル
    -0.07
    Converter
    -0.07
    :y
    -0.07
    Transmission
    -0.07
     transfer
    -0.07
    POSITIVE LOGITS
     unrestricted
    0.10
     knowingly
    0.09
    .Manifest
    0.09
     allegedly
    0.09
     соблюдать
    0.08
     говорится
    0.08
     দাবি
    0.08
     unstoppable
    0.08
     restrained
    0.08
     manifest
    0.08
    Activations Density 0.009%

    No Known Activations