© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 57
    Prev
    Next
    INDEX
    Explanations

    Orbital calculations

    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
    Duck
    -0.08
     multilingual
    -0.08
     Duck
    -0.07
     наш
    -0.07
     multinational
    -0.07
     tone
    -0.07
    ות
    -0.07
    ایی
    -0.07
     advocacy
    -0.07
    duck
    -0.07
    POSITIVE LOGITS
     llaw
    0.09
     gwe
    0.09
     solaire
    0.09
     κε
    0.08
     clinker
    0.08
     Тор
    0.08
    -primary
    0.08
     anao
    0.08
     leith
    0.08
    ὐ
    0.08
    Activations Density 0.002%

    No Known Activations