Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 56212
    Prev
    Next
    INDEX
    Explanations

    use, utility

    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
     schild
    -0.09
     usw
    -0.08
    صح
    -0.08
     cloud
    -0.08
     HSBC
    -0.08
     zul
    -0.08
    اران
    -0.07
    Cloud
    -0.07
    Normals
    -0.07
     oo
    -0.07
    POSITIVE LOGITS
    用途
    0.11
     usefulness
    0.10
     usable
    0.10
     utilidad
    0.10
     utile
    0.09
     útil
    0.09
     usos
    0.09
     ích
    0.08
     efficacité
    0.08
    usage
    0.08
    Activations Density 0.018%

    No Known Activations