© 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. 44606
    Prev
    Next
    INDEX
    Explanations

    BBQ

    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
    程
    -0.08
    .Operator
    -0.08
    程序
    -0.08
     homelessness
    -0.07
    ERATOR
    -0.07
     lad
    -0.07
    brook
    -0.07
    Born
    -0.07
    كتب
    -0.07
    Fred
    -0.07
    POSITIVE LOGITS
     dhab
    0.09
    .buffer
    0.08
     Fantastic
    0.08
     prakt
    0.08
     Dalam
    0.08
    .djangoproject
    0.08
     regard
    0.08
     ewu
    0.07
    ingu
    0.07
    _BUFFER
    0.07
    Activations Density 0.002%

    No Known Activations