© 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. 49091
    Prev
    Next
    INDEX
    Explanations

    更

    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
     bekomme
    -0.08
     Handy
    -0.08
    Вот
    -0.07
     reale
    -0.07
    真的吗
    -0.07
     bekommen
    -0.07
     switch
    -0.07
     lately
    -0.07
    Here's
    -0.07
    oys
    -0.07
    POSITIVE LOGITS
    强调
    0.32
    注
    0.31
     注
    0.28
     emphasizes
    0.26
     emphasize
    0.26
     enfat
    0.25
     emphasizing
    0.25
     emphasis
    0.23
     تاکید
    0.23
    追
    0.23
    Activations Density 0.054%

    No Known Activations