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. 58766
    Prev
    Next
    INDEX
    Explanations

    assistance

    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
     haja
    -0.09
     fabricate
    -0.08
     existência
    -0.08
     등장
    -0.08
     করি
    -0.08
     іс
    -0.08
     existencia
    -0.08
     يوجد
    -0.08
    ème
    -0.08
     interven
    -0.08
    POSITIVE LOGITS
     поможет
    0.13
     ayudará
    0.12
     helps
    0.12
    ช่วย
    0.11
     도움이
    0.11
     helping
    0.11
     помогут
    0.11
    帮助
    0.10
     позволит
    0.10
     helfen
    0.10
    Activations Density 0.178%

    No Known Activations