© 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. 64465
    Prev
    Next
    INDEX
    Explanations

    generics, type systems

    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
     poems
    -0.10
    shader
    -0.08
    诗
    -0.08
    ritur
    -0.08
     गीत
    -0.08
    料金
    -0.08
    歌词
    -0.08
    ังหว
    -0.08
     affid
    -0.08
    tempo
    -0.07
    POSITIVE LOGITS
     erased
    0.09
     EE
    0.08
     Recycling
    0.08
     recycling
    0.08
     näky
    0.08
     specificity
    0.08
    )("
    0.08
     recycl
    0.08
     recycle
    0.07
     TREE
    0.07
    Activations Density 0.002%

    No Known Activations