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. 53789
    Prev
    Next
    INDEX
    Explanations

    Non-English characters

    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
     vigor
    -0.08
    Applied
    -0.08
    Ix
    -0.07
    mall
    -0.07
    fort
    -0.07
    cci
    -0.07
     applied
    -0.07
    Origin
    -0.07
    kx
    -0.07
     yapılan
    -0.07
    POSITIVE LOGITS
     확인
    0.10
     여부
    0.09
     모르
    0.09
     தெரிய
    0.09
     বিশ
    0.09
     살
    0.08
    、お
    0.08
     বিস্তারিত
    0.08
     ખબર
    0.08
    確認
    0.08
    Activations Density 0.010%

    No Known Activations