© 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. 23-RESID-POST-AA
    11. 47620
    Prev
    Next
    INDEX
    Explanations

    上

    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
    noopener
    -0.08
     reckless
    -0.08
    060
    -0.08
    ikus
    -0.08
     Charg
    -0.08
     besucht
    -0.08
    /i
    -0.08
     einzigart
    -0.08
    iked
    -0.08
    ims
    -0.08
    POSITIVE LOGITS
    手
    0.17
     手
    0.14
     हाथ
    0.12
     கை
    0.12
     હાથ
    0.12
     చేత
    0.11
     ಕೈ
    0.11
     mão
    0.11
     hand
    0.10
     boat
    0.10
    Activations Density 0.001%

    No Known Activations