© 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. 65550
    Prev
    Next
    INDEX
    Explanations

    LinkedIn

    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
     costas
    -0.09
     wild
    -0.08
    竞
    -0.08
    transpose
    -0.08
     iterative
    -0.08
    urances
    -0.07
    etris
    -0.07
    firebase
    -0.07
    徴
    -0.07
     berühm
    -0.07
    POSITIVE LOGITS
     Workplace
    0.10
     workplace
    0.09
    /business
    0.09
    -business
    0.08
    商务
    0.08
     heavyweight
    0.08
     posting
    0.08
     blazer
    0.08
     workstation
    0.08
     Corporate
    0.08
    Activations Density 0.004%

    No Known Activations