© 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. 19-RESID-POST-AA
    11. 103060
    Prev
    Next
    INDEX
    Explanations

    Parenthetical phrases

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     verschiedenen
    -0.11
     forskjellige
    -0.11
     jeweiligen
    -0.10
     respective
    -0.10
     unterschiedlichen
    -0.10
     forskellige
    -0.10
     Various
    -0.10
     różnych
    -0.10
     различных
    -0.09
     verschillende
    -0.09
    POSITIVE LOGITS
    (Some
    0.10
     especially
    0.10
    (items
    0.09
     mindestens
    0.09
     alguns
    0.09
    (M
    0.09
    (item
    0.09
     some
    0.09
    (option
    0.09
     notably
    0.09
    Activations Density 0.009%

    No Known Activations