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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 63080
    Prev
    Next
    INDEX
    Explanations

    Reduce learning rate (ML)

    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
    oi
    -0.08
     Schwartz
    -0.08
     Fj
    -0.08
     antrop
    -0.07
     ethn
    -0.07
    publique
    -0.07
     मार्ग
    -0.07
     crime
    -0.07
     puzzle
    -0.07
     invitation
    -0.07
    POSITIVE LOGITS
    Optimizer
    0.10
    Monitoring
    0.10
    Stopping
    0.10
    Cooldown
    0.09
    监
    0.09
    Thresh
    0.09
    Monitor
    0.09
     Monitoring
    0.09
    .monitor
    0.09
    .Interval
    0.09
    Activations Density 0.001%

    No Known Activations