© 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. 94615
    Prev
    Next
    INDEX
    Explanations

    USE

    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
     parole
    -0.09
     των
    -0.08
    听
    -0.08
    隐
    -0.08
     قلم
    -0.08
     implant
    -0.08
    全集
    -0.08
     costas
    -0.08
     장소
    -0.08
    etite
    -0.08
    POSITIVE LOGITS
    0.08
    .form
    0.07
    545
    0.07
    cox
    0.07
    Conversion
    0.07
    .tax
    0.07
    Nag
    0.07
    lua
    0.07
     Debian
    0.07
     retained
    0.07
    Activations Density 0.001%
    No Known Activations