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. 120182
    Prev
    Next
    INDEX
    Explanations

    Isopropyl alcohol

    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
     Viet
    -0.10
    Menus
    -0.08
    载
    -0.08
     population
    -0.07
     încă
    -0.07
     ouverte
    -0.07
     cmds
    -0.07
     Geschäfts
    -0.07
     تس
    -0.07
    aea
    -0.07
    POSITIVE LOGITS
    ęt
    0.08
     Hue
    0.08
     Skype
    0.07
     柳
    0.07
     beaucoup
    0.07
     ან
    0.07
    nag
    0.07
     వచ్చ
    0.07
    /bg
    0.07
     nag
    0.07
    Activations Density 0.000%

    No Known Activations