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

    Neuronpedia

    APICircuit 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. 23-RESID-POST-AA
    6. 98215
    Prev
    Next
    INDEX
    Explanations

    period

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     rohkem
    -0.09
     lohnt
    -0.09
    روعات
    -0.07
     enlargement
    -0.07
     higit
    -0.07
    udding
    -0.07
    √
    -0.07
     اكثر
    -0.07
     √
    -0.07
    λέον
    -0.07
    POSITIVE LOGITS
     comply
    0.28
     ethical
    0.27
    免责声明
    0.26
    倫理
    0.26
     respectful
    0.26
     disclaimer
    0.26
     Ethical
    0.26
     legality
    0.25
    免责
    0.24
     complies
    0.24
    Activations Density 0.331%

    No Known Activations