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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 111506
    Prev
    Next
    INDEX
    Explanations

    end of life

    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
     INVENT
    -0.08
     REQUIRE
    -0.08
    .apps
    -0.08
     Currency
    -0.08
     Capitol
    -0.08
    _maps
    -0.08
     currency
    -0.08
    >↵///
    -0.08
     TLC
    -0.08
    іп
    -0.08
    POSITIVE LOGITS
     euth
    0.12
     मृत्यु
    0.11
     пациент
    0.10
     прекращ
    0.10
     hospice
    0.10
     смерть
    0.10
     Schmerz
    0.10
    alliative
    0.10
     दर्द
    0.10
     मौत
    0.10
    Activations Density 0.028%

    No Known Activations