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. 15-RESID-POST-AA
    6. 124
    Prev
    Next
    INDEX
    Explanations

    Monika, Natsuki, Yuri, Sayori

    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
     поряд
    -0.08
    !↵↵
    -0.08
    867
    -0.08
    ไ
    -0.07
     ।↵↵
    -0.07
     `.
    -0.07
     day
    -0.07
    `.↵↵
    -0.07
     club
    -0.07
     united
    -0.07
    POSITIVE LOGITS
     texts
    0.09
     ATV
    0.09
     Voices
    0.09
    ervolgens
    0.08
    íbula
    0.08
     voices
    0.08
     徐
    0.08
     Bộ
    0.08
     Oste
    0.08
     voces
    0.08
    Activations Density 0.018%

    No Known Activations