© 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. 108127
    Prev
    Next
    INDEX
    Explanations

    The Outsiders

    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
     lägga
    -0.08
     för
    -0.07
     يقوم
    -0.07
     کب
    -0.07
    lut
    -0.07
     agregar
    -0.07
     bw
    -0.07
     agrega
    -0.07
     در
    -0.07
     بي
    -0.07
    POSITIVE LOGITS
     inflamm
    0.09
     defeats
    0.08
    !");
    ↵
    0.08
    aisen
    0.08
     eps
    0.08
    躁
    0.08
    afet
    0.08
     pains
    0.08
    ")+
    0.08
    Destructor
    0.08
    Activations Density 0.000%

    No Known Activations