Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 90066
    Prev
    Next
    INDEX
    Explanations

    Dates and numbers

    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
     professionally
    -0.08
    -resolution
    -0.08
    -marker
    -0.08
    -panel
    -0.08
     तत
    -0.07
    рофессион
    -0.07
    ्रो
    -0.07
    issement
    -0.07
    -ro
    -0.07
    िध
    -0.07
    POSITIVE LOGITS
    871
    0.09
     consciousness
    0.08
    pee
    0.08
    icho
    0.07
     osv
    0.07
    月份
    0.07
    Gregorian
    0.07
     Тел
    0.07
    meno
    0.07
    Important
    0.07
    Activations Density 0.008%

    No Known Activations