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. 46709
    Prev
    Next
    INDEX
    Explanations

    power absorption

    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
     reassuring
    -0.08
    ুস
    -0.07
    уқ
    -0.07
    urun
    -0.07
    аяв
    -0.07
    ряд
    -0.07
     kirjo
    -0.07
     הכר
    -0.07
    iew
    -0.07
    ুপ
    -0.07
    POSITIVE LOGITS
     Assim
    0.12
    Assim
    0.11
     assimilation
    0.11
     assimil
    0.11
     absorbs
    0.10
     خز
    0.10
     enemy
    0.10
    .enemy
    0.10
     чуж
    0.10
     získ
    0.09
    Activations Density 0.037%

    No Known Activations