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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 46423
    Prev
    Next
    INDEX
    Explanations

    Up

    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
     acoust
    -0.08
    lift
    -0.08
    -0.07
    మైన
    -0.07
     spro
    -0.07
    fear
    -0.07
     lifted
    -0.07
     brz
    -0.07
    zcan
    -0.07
     stamped
    -0.07
    POSITIVE LOGITS
     Garda
    0.08
    元
    0.08
    詢
    0.08
     Merry
    0.08
    TL
    0.07
    跟
    0.07
     sui
    0.07
    arpa
    0.07
    ary
    0.07
    电话
    0.07
    Activations Density 0.009%

    No Known Activations