© 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. 79201
    Prev
    Next
    INDEX
    Explanations

    excluding

    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
     competence
    -0.08
    jong
    -0.08
     ચાલુ
    -0.08
    znym
    -0.08
     continual
    -0.07
    jni
    -0.07
    .Pr
    -0.07
    盘
    -0.07
    lyn
    -0.07
     dns
    -0.07
    POSITIVE LOGITS
     precious
    0.09
    Duplicates
    0.08
    ॉफ
    0.08
    _duplicates
    0.08
     Vergangenheit
    0.08
    建筑
    0.07
     prefix
    0.07
     duplicates
    0.07
    ，更
    0.07
    ////
    0.07
    Activations Density 0.019%

    No Known Activations