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. 23574
    Prev
    Next
    INDEX
    Explanations

    just

    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
     Niet
    -0.09
     Minimum
    -0.08
     Mask
    -0.08
     jargon
    -0.08
     Juven
    -0.08
    .Minimum
    -0.08
     instr
    -0.08
     Instr
    -0.07
     viz
    -0.07
    stas
    -0.07
    POSITIVE LOGITS
    اصيل
    0.08
    لی
    0.08
    لقد
    0.08
    ?
    0.08
    ,如果
    0.08
     '//
    0.08
    ليق
    0.08
    راز
    0.08
    ccoli
    0.08
    λεγ
    0.07
    Activations Density 0.004%

    No Known Activations