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. 55969
    Prev
    Next
    INDEX
    Explanations

    Parts of things or materials

    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
     أثر
    -0.08
    Linea
    -0.07
     своев
    -0.07
    -looking
    -0.07
    -headed
    -0.07
     vom
    -0.07
    warden
    -0.07
     Seri
    -0.07
     borrowing
    -0.07
    ುದ್ದ
    -0.07
    POSITIVE LOGITS
     वाला
    0.11
     वाली
    0.10
     கொண்ட
    0.09
    മുള്ള
    0.09
     वाले
    0.09
     ਵਾਲ
    0.08
    、高
    0.08
     ունեցող
    0.08
     والے
    0.08
    ensure
    0.08
    Activations Density 0.211%

    No Known Activations