© 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. 7-RESID-POST-AA
    11. 1097
    Prev
    Next
    INDEX
    Explanations

    preschool

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     presidential
    -0.08
     sheet
    -0.07
     앞으로
    -0.07
     Stafford
    -0.07
    recv
    -0.07
     Fernandes
    -0.07
     sheets
    -0.07
    ્ર
    -0.07
     فإن
    -0.07
     فإنه
    -0.07
    POSITIVE LOGITS
    时期
    0.11
    阶段
    0.08
    止
    0.08
    学历
    0.08
    梦想
    0.08
    期间
    0.08
     anthrop
    0.08
     Atem
    0.07
    teen
    0.07
    动画
    0.07
    Activations Density 0.002%

    No Known Activations