© 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. 23-RESID-POST-AA
    11. 5966
    Prev
    Next
    INDEX
    Explanations

    Numerical data or code snippets

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     সুব
    -0.09
     快
    -0.08
     ডেস্ক
    -0.08
     schnellen
    -0.08
     vermeld
    -0.08
     آلة
    -0.08
     bureau
    -0.08
     carcinoma
    -0.07
     rap
    -0.07
    imeter
    -0.07
    POSITIVE LOGITS
     An
    0.08
    An
    0.08
    >An
    0.08
    ří
    0.07
    _numeric
    0.07
    øre
    0.07
    цами
    0.07
    Numeric
    0.07
    -spacing
    0.07
    oving
    0.07
    Activations Density 0.009%

    No Known Activations