© 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. 23-RESID-POST-AA
    11. 96218
    Prev
    Next
    INDEX
    Explanations

    busy

    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
     degradation
    -0.09
     alent
    -0.08
     degrade
    -0.08
     degrading
    -0.08
    ahay
    -0.07
     degrad
    -0.07
     degraded
    -0.07
     pokoj
    -0.07
     neer
    -0.07
    %^
    -0.07
    POSITIVE LOGITS
    忙
    0.36
     busy
    0.34
     hectic
    0.33
    busy
    0.29
    Busy
    0.29
     Busy
    0.29
    _busy
    0.28
     kiire
    0.26
     ocupado
    0.26
    _BUSY
    0.24
    Activations Density 0.130%

    No Known Activations