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. 458
    Prev
    Next
    INDEX
    Explanations

    争

    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
     roto
    -0.09
    firm
    -0.08
    woch
    -0.08
     dna
    -0.07
    ్టర్
    -0.07
     hyster
    -0.07
     Mani
    -0.07
     Firm
    -0.07
     erm
    -0.07
    Firm
    -0.07
    POSITIVE LOGITS
    争
    0.08
     ಅವಕಾಶ
    0.08
    ;;
    0.07
     upsetting
    0.07
    ಿಗಾಗಿ
    0.07
     showing
    0.07
    مس
    0.07
    measure
    0.07
     tribun
    0.07
    quota
    0.07
    Activations Density 0.002%

    No Known Activations