© 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. 108498
    Prev
    Next
    INDEX
    Explanations

    12

    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
     deduction
    -0.08
     boule
    -0.08
    اهد
    -0.08
     militia
    -0.08
     huil
    -0.07
     freelancers
    -0.07
     liability
    -0.07
     Directors
    -0.07
    ожд
    -0.07
     Adult
    -0.07
    POSITIVE LOGITS
     chew
    0.08
     Shelley
    0.07
    .decor
    0.07
     잘
    0.07
    _l
    0.07
     dap
    0.07
     trama
    0.07
     encounter
    0.07
     wearable
    0.07
     [];↵
    0.07
    Activations Density 0.000%

    No Known Activations