© 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. 95733
    Prev
    Next
    INDEX
    Explanations

    admit

    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
     indicative
    -0.08
    олага
    -0.08
    _SUFFIX
    -0.07
     Ident
    -0.07
    verse
    -0.07
    яг
    -0.07
     बिग
    -0.07
     इंटर
    -0.07
    اضية
    -0.07
    oise
    -0.07
    POSITIVE LOGITS
    .Visit
    0.08
     ultrices
    0.08
     ainda
    0.08
    .Initialize
    0.08
    .Draw
    0.08
    	This
    0.08
    .Temp
    0.08
     meios
    0.08
     masih
    0.08
     κάπο
    0.08
    Activations Density 0.002%

    No Known Activations