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. 106208
    Prev
    Next
    INDEX
    Explanations

    cool

    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
     Gold
    -0.08
     Wenn
    -0.08
    Gold
    -0.08
    software
    -0.08
    ako
    -0.07
    also
    -0.07
     Vans
    -0.07
    ematic
    -0.07
    vec
    -0.07
    άζεται
    -0.07
    POSITIVE LOGITS
     ماحول
    0.08
    (cs
    0.08
    (can
    0.08
     raf
    0.08
    ixe
    0.08
     terlebih
    0.08
    (er
    0.08
     ย
    0.08
    astro
    0.08
     ioutil
    0.07
    Activations Density 0.002%

    No Known Activations