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. 30609
    Prev
    Next
    INDEX
    Explanations

    ->

    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
    Rep
    -0.08
     origins
    -0.08
    Origins
    -0.08
    That
    -0.07
     nimmt
    -0.07
     ور
    -0.07
    -0.07
    rep
    -0.07
    CO
    -0.07
     wob
    -0.07
    POSITIVE LOGITS
     summarize
    0.08
    ುದ
    0.08
     Nikki
    0.07
     Kh
    0.07
     Quer
    0.07
     reina
    0.07
     unauthorized
    0.07
     Pang
    0.07
     discharge
    0.07
     Pach
    0.07
    Activations Density 0.002%

    No Known Activations