© 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. 11-RESID-POST-AA
    11. 78059
    Prev
    Next
    INDEX
    Explanations

    selective

    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
     Temper
    -0.08
    hältnis
    -0.08
     square
    -0.07
    -0.07
     daughters
    -0.07
     relax
    -0.07
    temper
    -0.07
    wür
    -0.07
    ca
    -0.07
     territori
    -0.07
    POSITIVE LOGITS
     selective
    0.14
     selet
    0.12
    Selective
    0.12
     selectively
    0.11
     Filtering
    0.11
     Filter
    0.11
    .Filter
    0.11
    (Filter
    0.11
    过滤
    0.10
     filtro
    0.10
    Activations Density 0.011%
    No Known Activations