© 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. 95664
    Prev
    Next
    INDEX
    Explanations

    zip

    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
     erzielt
    -0.09
     că
    -0.08
     erzielen
    -0.08
    บาล
    -0.07
    ண்டும்
    -0.07
    �
    -0.07
    壮
    -0.07
    moor
    -0.07
    vek
    -0.07
    وبة
    -0.07
    POSITIVE LOGITS
    -Ver
    0.09
    .loads
    0.09
     الإلكتروني
    0.08
    esty
    0.08
     houses
    0.07
     pragmatic
    0.07
    .dumps
    0.07
     cutter
    0.07
     temper
    0.07
     transit
    0.07
    Activations Density 0.003%

    No Known Activations