© 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. 11-RESID-POST-AA
    11. 63278
    Prev
    Next
    INDEX
    Explanations

    skeleton

    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
     solver
    -0.08
    -0.08
     Handle
    -0.07
     irrational
    -0.07
     employ
    -0.07
     entrant
    -0.07
    ]++;↵
    -0.07
     bell
    -0.07
     constantes
    -0.07
    vine
    -0.07
    POSITIVE LOGITS
    Vid
    0.08
     Vid
    0.08
     Yuk
    0.08
     eth
    0.08
     cili
    0.08
    .et
    0.07
     Inj
    0.07
     Eth
    0.07
    .default
    0.07
    quarters
    0.07
    Activations Density 0.003%
    No Known Activations