© 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. 65591
    Prev
    Next
    INDEX
    Explanations

    |

    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
    862
    -0.09
     REC
    -0.08
     volant
    -0.08
    ...?
    -0.07
    arb
    -0.07
     resident
    -0.07
     alterar
    -0.07
    ???
    -0.07
     Meister
    -0.07
     Cannot
    -0.07
    POSITIVE LOGITS
    其次
    0.08
    还
    0.08
     iluminación
    0.07
    энд
    0.07
     dressed
    0.07
    购物
    0.07
     gön
    0.07
    Shopping
    0.07
    ៅ
    0.07
     manicure
    0.07
    Activations Density 0.014%

    No Known Activations