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. 12065
    Prev
    Next
    INDEX
    Explanations

    heresy and suppression

    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
     trape
    -0.09
     Enjoy
    -0.08
    Nik
    -0.08
    τ
    -0.08
    TA
    -0.08
     enjoy
    -0.07
    Nal
    -0.07
    Enjoy
    -0.07
    -0.07
    IZA
    -0.07
    POSITIVE LOGITS
     fuite
    0.10
     undesirable
    0.09
     unacceptable
    0.09
     deemed
    0.08
    0.08
     deviation
    0.08
     unwanted
    0.08
    乱子
    0.08
    另类
    0.08
    Counter
    0.08
    Activations Density 0.031%

    No Known Activations