© 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. 19-RESID-POST-AA
    11. 102399
    Prev
    Next
    INDEX
    Explanations

    mathematical sequences/trends

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _MATCH
    -0.09
    Denied
    -0.09
     coords
    -0.08
     DEFAULT
    -0.08
    匹
    -0.08
     denied
    -0.08
     Consent
    -0.08
    Consent
    -0.08
    秒速
    -0.08
    -License
    -0.08
    POSITIVE LOGITS
     consecut
    0.14
     consecutive
    0.13
     trend
    0.13
     decreasing
    0.12
     sequence
    0.12
     growth
    0.11
    Trend
    0.11
     discrete
    0.11
     decreases
    0.11
     integer
    0.11
    Activations Density 0.030%

    No Known Activations