© 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. 102894
    Prev
    Next
    INDEX
    Explanations

    Code and math

    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
     и
    -0.10
     và
    -0.10
     және
    -0.09
     અને
    -0.09
     sareng
    -0.09
    њ
    -0.09
     ۽
    -0.09
     și
    -0.09
    illugit
    -0.09
     និង
    -0.09
    POSITIVE LOGITS
    ल
    0.09
    第一页
    0.08
    分钟前
    0.08
     craze
    0.08
    都会
    0.08
    越
    0.07
    会上
    0.07
     Tehran
    0.07
    डेट
    0.07
    小时前
    0.07
    Activations Density 0.000%

    No Known Activations