© 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. 94921
    Prev
    Next
    INDEX
    Explanations

    Pricing/money

    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
     위험
    -0.09
     доступа
    -0.09
    ormány
    -0.08
    Ế
    -0.08
     감독
    -0.08
    othe
    -0.08
     aanmerking
    -0.08
    큼
    -0.08
     기간
    -0.08
     μετά
    -0.08
    POSITIVE LOGITS
    fake
    0.14
     fake
    0.12
    dummy
    0.12
    _dummy
    0.12
     dummy
    0.12
     Fake
    0.11
    _fake
    0.11
     bogus
    0.11
    (dummy
    0.11
    (fake
    0.11
    Activations Density 0.027%

    No Known Activations