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. 112004
    Prev
    Next
    INDEX
    Explanations

    Minecraft building

    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
     течение
    -0.08
     спе
    -0.08
     insiders
    -0.08
     postpon
    -0.08
    _DURATION
    -0.08
    _duration
    -0.08
    лек
    -0.07
     众
    -0.07
    -duration
    -0.07
     episod
    -0.07
    POSITIVE LOGITS
     Anfänger
    0.09
    .normal
    0.08
    mun
    0.07
     शुरुआ
    0.07
     logically
    0.07
     rampant
    0.07
     architectural
    0.07
     towering
    0.07
     sane
    0.07
     declaring
    0.07
    Activations Density 0.011%

    No Known Activations