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. 76472
    Prev
    Next
    INDEX
    Explanations

    Science and technology texts

    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
    enticate
    -0.08
    poke
    -0.08
    mad
    -0.08
    鸭
    -0.08
     exciting
    -0.07
    järel
    -0.07
     深
    -0.07
    ورة
    -0.07
    ạp
    -0.07
    фера
    -0.07
    POSITIVE LOGITS
     posl
    0.07
    _needed
    0.07
    無し
    0.07
    .com's
    0.07
     multiplic
    0.07
     siin
    0.07
     έναν
    0.07
    RH
    0.07
     वाला
    0.07
     RF
    0.07
    Activations Density 0.101%

    No Known Activations