© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 47753
    Prev
    Next
    INDEX
    Explanations

    just

    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
     tento
    -0.08
     Tento
    -0.08
    pla
    -0.08
    beaut
    -0.08
     lover
    -0.07
    -0.07
    .br
    -0.07
    .case
    -0.07
     Obs
    -0.07
     Ugly
    -0.07
    POSITIVE LOGITS
    几年
    0.10
    তম
    0.10
    तम
    0.10
     transition
    0.09
     appena
    0.09
    颖
    0.09
     influx
    0.08
    ిశ
    0.08
    -fashioned
    0.08
     selesai
    0.08
    Activations Density 0.017%

    No Known Activations