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. 27768
    Prev
    Next
    INDEX
    Explanations

    plotting code

    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
     deterministic
    -0.08
     سرا
    -0.08
     determin
    -0.08
     personagens
    -0.08
     విచ
    -0.08
     विश्व
    -0.07
    特殊
    -0.07
     Chez
    -0.07
    ทั้ง
    -0.07
    主体
    -0.07
    POSITIVE LOGITS
     лиценз
    0.09
    -saving
    0.08
    -running
    0.08
    _latest
    0.08
    spielen
    0.08
     Gambling
    0.08
     OLD
    0.07
     Alltag
    0.07
    .pyplot
    0.07
    Latest
    0.07
    Activations Density 0.001%

    No Known Activations