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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 49128
    Prev
    Next
    INDEX
    Explanations

    set

    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
    he
    -0.09
    /
    -0.08
     Victorian
    -0.07
     did
    -0.07
    editor
    -0.07
     chatbot
    -0.07
     poem
    -0.07
     findest
    -0.07
    his
    -0.07
    `;↵↵
    -0.07
    POSITIVE LOGITS
    FFD
    0.09
     MATRIX
    0.08
    更新时间
    0.08
    -अ
    0.08
     knit
    0.08
     undesirable
    0.08
     Tess
    0.08
     substant
    0.08
    queles
    0.08
    Agree
    0.08
    Activations Density 0.000%

    No Known Activations