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

    Neuronpedia

    APICircuit 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. 53942
    Prev
    Next
    INDEX
    Explanations

    Writing or Descriptions

    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
    اتو
    -0.08
     produkt
    -0.08
     subst
    -0.07
     refl
    -0.07
    indt
    -0.07
     plural
    -0.07
    aturbate
    -0.07
     corpus
    -0.07
    Corpus
    -0.07
     ↵↵
    -0.07
    POSITIVE LOGITS
    zc
    0.08
    ходим
    0.08
     reservado
    0.07
     bedrijf
    0.07
     ocasião
    0.07
     grab
    0.07
    печ
    0.07
     benod
    0.07
     você
    0.07
    жение
    0.07
    Activations Density 0.431%

    No Known Activations