© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 23-RESID-POST-AA
    11. 50710
    Prev
    Next
    INDEX
    Explanations

    say car parts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Rebecca
    -0.09
     chaining
    -0.09
     supervise
    -0.08
     supervision
    -0.08
    .chain
    -0.08
     chains
    -0.08
    extern
    -0.08
     plomberie
    -0.08
     lavander
    -0.08
     cranes
    -0.08
    POSITIVE LOGITS
    仪
    0.12
     dashboard
    0.11
    dashboard
    0.11
     instrument
    0.11
     Dashboard
    0.10
     shift
    0.10
    shift
    0.10
     dash
    0.10
     داش
    0.10
    方向
    0.10
    Activations Density 0.007%

    No Known Activations