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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 43698
    Prev
    Next
    INDEX
    Explanations

    young/origins

    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
    asper
    -0.10
    整
    -0.09
    .YES
    -0.08
     نعم
    -0.08
    örper
    -0.08
     серьез
    -0.08
     বিজ
    -0.08
    ‌اند
    -0.08
    /Web
    -0.07
     bestehen
    -0.07
    POSITIVE LOGITS
     footage
    0.09
     depicting
    0.09
     모습을
    0.09
     ран
    0.09
    fance
    0.08
     infancy
    0.08
    預
    0.08
     jungen
    0.08
    วัย
    0.08
     pre
    0.08
    Activations Density 0.044%

    No Known Activations