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. 15-RESID-POST-AA
    6. 19447
    Prev
    Next
    INDEX
    Explanations

    hyp

    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_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     תמיד
    -0.08
    фти
    -0.08
     ਇੱਕ
    -0.08
    idot
    -0.08
    weist
    -0.08
     ఒక
    -0.08
    anion
    -0.08
     Mensch
    -0.08
     një
    -0.08
    fäh
    -0.08
    POSITIVE LOGITS
    이며
    0.09
     puisque
    0.08
     little
    0.08
     puisqu
    0.08
     since
    0.08
     tandis
    0.08
    이고
    0.08
    -like
    0.08
    とな
    0.07
    หลัก
    0.07
    Activations Density 0.012%

    No Known Activations