© 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. 30099
    Prev
    Next
    INDEX
    Explanations

    small size

    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
    顺
    -0.08
     நடத்த
    -0.08
     suaves
    -0.08
    apé
    -0.08
     suav
    -0.08
    .Ordinal
    -0.08
    Lst
    -0.07
     செய்வ
    -0.07
     spontaneous
    -0.07
    least
    -0.07
    POSITIVE LOGITS
     cramped
    0.11
     appartement
    0.10
     taille
    0.09
     квартира
    0.09
     spazio
    0.09
     apartamento
    0.09
     आकार
    0.08
     квартире
    0.08
     ukuran
    0.08
     espace
    0.08
    Activations Density 0.026%

    No Known Activations