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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 120353
    Prev
    Next
    INDEX
    Explanations

    key

    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
     AGO
    -0.08
    �
    -0.08
     आठ
    -0.08
     quotidienne
    -0.08
     ginger
    -0.08
     audible
    -0.08
     Aga
    -0.08
     schip
    -0.08
     Etc
    -0.08
     tù
    -0.07
    POSITIVE LOGITS
    .constraint
    0.08
     Tale
    0.08
    広
    0.08
    /met
    0.08
     Flor
    0.07
     wide
    0.07
     ઉપર
    0.07
    ometri
    0.07
     veloc
    0.07
     payoff
    0.07
    Activations Density 0.002%

    No Known Activations