© 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. 96404
    Prev
    Next
    INDEX
    Explanations

    ++

    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
    ;
    -0.11
    verband
    -0.08
    wire
    -0.08
    Axes
    -0.08
    ++++
    -0.08
    +++
    -0.08
    ++++++++
    -0.08
    reman
    -0.08
    Rem
    -0.07
    ikelihood
    -0.07
    POSITIVE LOGITS
    。）
    0.07
    +#
    0.07
     toward
    0.07
     laatste
    0.07
    怎么样
    0.07
     bás
    0.07
     അട
    0.07
    0.07
     ప్రారంభ
    0.07
     PES
    0.07
    Activations Density 0.003%
    No Known Activations