© 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 EvalsExportsAPI 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. 43593
    Prev
    Next
    INDEX
    Explanations

    scientific/technical detergents

    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
     Primavera
    -0.08
    -sign
    -0.08
     dipl
    -0.08
    .Sign
    -0.08
     diploma
    -0.08
    签
    -0.07
     burning
    -0.07
     lectures
    -0.07
    말
    -0.07
    cott
    -0.07
    POSITIVE LOGITS
    _EXTRA
    0.09
     deterg
    0.08
     detergent
    0.08
    ە
    0.08
    יטי
    0.08
     Sek
    0.08
     тк
    0.08
     kondisyon
    0.07
    zustellen
    0.07
     suav
    0.07
    Activations Density 0.001%

    No Known Activations