Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 58622
    Prev
    Next
    INDEX
    Explanations

    medication reversal

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     adolescence
    -0.07
     persu
    -0.07
     onwards
    -0.07
     input
    -0.07
    עה
    -0.07
     العالية
    -0.07
    16
    -0.07
    .beh
    -0.07
    /value
    -0.07
     نق
    -0.07
    POSITIVE LOGITS
     компенса
    0.10
     компен
    0.10
     detox
    0.09
    逆
    0.09
    救
    0.09
     desf
    0.09
     pihak
    0.09
     mitigate
    0.09
     cancelling
    0.09
     mitigating
    0.08
    Activations Density 0.011%

    No Known Activations