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. 119144
    Prev
    Next
    INDEX
    Explanations

    aging

    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
     pertandingan
    -0.08
     Random
    -0.07
    gas
    -0.07
     Epstein
    -0.07
    \ORM
    -0.07
     דרך
    -0.07
     ਤ
    -0.07
    idor
    -0.07
     lagu
    -0.07
     espont
    -0.07
    POSITIVE LOGITS
    越来越
    0.10
     retiring
    0.09
     retirement
    0.09
     населения
    0.08
     widow
    0.08
     emerging
    0.08
     retire
    0.08
     aposent
    0.08
    .shutdown
    0.08
     piling
    0.08
    Activations Density 0.009%

    No Known Activations