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. 43992
    Prev
    Next
    INDEX
    Explanations

    achieving goals

    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
    -called
    -0.09
    chets
    -0.08
     ishl
    -0.08
     작업
    -0.08
     trabalhos
    -0.08
    comings
    -0.07
    chet
    -0.07
     glow
    -0.07
     Gr
    -0.07
    krank
    -0.07
    POSITIVE LOGITS
    措施
    0.11
     الممكن
    0.11
     لتحقيق
    0.11
     imaginable
    0.10
     средство
    0.10
    เพื่อ
    0.10
     Maßnahmen
    0.09
     maatregelen
    0.09
     لض
    0.09
     меры
    0.09
    Activations Density 0.024%

    No Known Activations