© 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. 44675
    Prev
    Next
    INDEX
    Explanations

    SSH keys

    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
     fraternity
    -0.09
    017
    -0.08
    াংশ
    -0.08
    驾驶
    -0.08
    ేర
    -0.08
     বহ
    -0.08
    责
    -0.08
     কাছে
    -0.07
     conocida
    -0.07
    .signature
    -0.07
    POSITIVE LOGITS
     generation
    0.09
    .generate
    0.09
     Generate
    0.08
     spotify
    0.08
     generations
    0.08
    Generate
    0.08
    .Generate
    0.08
     generates
    0.08
     hoje
    0.08
     Recommended
    0.08
    Activations Density 0.003%

    No Known Activations