© 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. 102945
    Prev
    Next
    INDEX
    Explanations

    Medications

    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
     galleries
    -0.10
     Enlight
    -0.10
     Portrait
    -0.09
     đẹp
    -0.09
     Galleries
    -0.09
    portrait
    -0.09
    精彩
    -0.09
     portraits
    -0.09
     Haunted
    -0.09
     idyllic
    -0.09
    POSITIVE LOGITS
     препараты
    0.30
     medications
    0.28
     препарат
    0.28
     drugs
    0.27
    药
    0.26
     medication
    0.25
     препарата
    0.25
     препаратов
    0.24
    薬
    0.24
     препара
    0.23
    Activations Density 0.037%

    No Known Activations