© 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. 97545
    Prev
    Next
    INDEX
    Explanations

    为

    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
     assumes
    -0.09
    נחנו
    -0.09
    爽
    -0.09
     tankou
    -0.09
    ופר
    -0.08
     helps
    -0.08
     fores
    -0.08
     teaches
    -0.08
     nagbibigay
    -0.08
    ่าง
    -0.08
    POSITIVE LOGITS
     better
    0.15
     besser
    0.13
     лучше
    0.13
     увеличить
    0.13
     добиться
    0.13
     besseren
    0.13
     повыс
    0.12
     сниз
    0.12
     избежать
    0.12
    应
    0.12
    Activations Density 0.017%

    No Known Activations