© 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. 26573
    Prev
    Next
    INDEX
    Explanations

    Dialogue

    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
    agrance
    -0.09
     돌아
    -0.09
    istr
    -0.08
     pariatur
    -0.08
    ührung
    -0.08
    obiles
    -0.08
     килом
    -0.08
    бав
    -0.08
    ledu
    -0.08
    adians
    -0.08
    POSITIVE LOGITS
     stock
    0.08
    storage
    0.07
     placeholder
    0.07
     funnel
    0.07
     স্থান
    0.07
     কাউ
    0.07
    .def
    0.07
    丰富
    0.06
     যেন
    0.06
     রাজ
    0.06
    Activations Density 0.021%

    No Known Activations