© 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. 23-RESID-POST-AA
    11. 50760
    Prev
    Next
    INDEX
    Explanations

    data collection/metrics

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     আদাল
    -0.10
    法院
    -0.09
     judicial
    -0.09
     കോടതി
    -0.09
     forgiveness
    -0.09
    残局
    -0.09
    .undo
    -0.09
     forgiving
    -0.09
    司法
    -0.09
     courtroom
    -0.09
    POSITIVE LOGITS
    采
    0.20
     agent
    0.19
     collectors
    0.19
     Sampling
    0.19
     metric
    0.19
    Sampling
    0.19
     Metric
    0.19
     sampling
    0.19
    Metric
    0.19
     Collector
    0.19
    Activations Density 0.027%

    No Known Activations