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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 54335
    Prev
    Next
    INDEX
    Explanations

    exponential backoff retries

    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
     MDF
    -0.08
     Accountability
    -0.08
     uphold
    -0.07
     IVA
    -0.07
    _annotation
    -0.07
     만족
    -0.07
     behalen
    -0.07
    .Appearance
    -0.07
     accountability
    -0.07
     marcador
    -0.07
    POSITIVE LOGITS
     retries
    0.11
    retry
    0.11
     exponentially
    0.10
     exponential
    0.10
    Retry
    0.10
     retry
    0.10
     spacing
    0.10
     Retry
    0.10
     cooldown
    0.09
    allback
    0.09
    Activations Density 0.001%

    No Known Activations