© 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. 19-RESID-POST-AA
    11. 103177
    Prev
    Next
    INDEX
    Explanations

    pix

    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
    measurement
    -0.08
    consider
    -0.08
    confidence
    -0.08
    elong
    -0.07
    αγ
    -0.07
    ltr
    -0.07
    iteration
    -0.07
    lights
    -0.07
    aint
    -0.07
     কেই
    -0.07
    POSITIVE LOGITS
    有限公司官网
    0.11
    中心官网
    0.10
    ിൽ
    0.10
    机官网
    0.09
    论坛
    0.09
    '].
    0.09
    有限公司
    0.09
    ьев
    0.09
    '].'
    0.09
    彩票网
    0.09
    Activations Density 0.009%

    No Known Activations