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

    Neuronpedia

    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. 23-RESID-POST-AA
    11. 6684
    Prev
    Next
    INDEX
    Explanations

    replies

    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
     stora
    -0.10
    贷款
    -0.08
     logement
    -0.08
     altas
    -0.08
     convenience
    -0.08
     thuận
    -0.08
     subplot
    -0.08
     suplemento
    -0.07
     barnet
    -0.07
     Freizeit
    -0.07
    POSITIVE LOGITS
    返信
    0.15
     conveys
    0.14
     FIVE
    0.13
    回复
    0.13
     reply
    0.13
    reply
    0.13
     five
    0.13
     回复
    0.13
     conveying
    0.13
     RESPONSE
    0.13
    Activations Density 0.039%

    No Known Activations