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. 119664
    Prev
    Next
    INDEX
    Explanations

    squared terms

    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
     faint
    -0.08
    junto
    -0.08
    โด
    -0.08
    お気
    -0.08
     located
    -0.07
     pilot
    -0.07
     Espan
    -0.07
     atten
    -0.07
     હ
    -0.07
    :"",↵
    -0.07
    POSITIVE LOGITS
     talu
    0.08
     (€
    0.07
     unpar
    0.07
     MATERIAL
    0.07
    Pics
    0.07
     Woll
    0.07
    (total
    0.07
     medd
    0.07
    .$$
    0.07
     Mittel
    0.07
    Activations Density 0.080%

    No Known Activations