© 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. 3-RESID-POST-AA
    11. 13165
    Prev
    Next
    INDEX
    Explanations

    ど

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     lining
    -0.09
     Camps
    -0.09
    -0.08
     Vine
    -0.08
     आउ
    -0.07
    alai
    -0.07
    УР
    -0.07
     shrub
    -0.07
     Cov
    -0.07
     ruo
    -0.07
    POSITIVE LOGITS
     ginger
    0.07
    ку
    0.07
    ッ
    0.07
    标
    0.07
    標
    0.07
     bancos
    0.07
     hi
    0.07
    Adv
    0.07
     unik
    0.07
    }],↵
    0.07
    Activations Density 0.000%
    No Known Activations