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. 19377
    Prev
    Next
    INDEX
    Explanations

    requests

    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
     unsuitable
    -0.09
    ВД
    -0.08
     breakthroughs
    -0.08
    աբար
    -0.08
     yüzden
    -0.08
     امله
    -0.08
     därför
    -0.08
     бед
    -0.08
     لارې
    -0.08
     entonces
    -0.08
    POSITIVE LOGITS
     potentially
    0.10
     somewhat
    0.09
     Certaines
    0.08
     presumably
    0.08
     [↵
    0.08
     zwar
    0.08
     möglicherweise
    0.08
    涉及
    0.08
     Hoewel
    0.08
    possibly
    0.08
    Activations Density 0.041%

    No Known Activations