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. 59185
    Prev
    Next
    INDEX
    Explanations

    comma

    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
    .commun
    -0.07
    _issue
    -0.07
     coh
    -0.07
    .Parser
    -0.07
     ಏ
    -0.07
     subs
    -0.07
     erken
    -0.07
     मुद्द
    -0.07
     champs
    -0.07
    _parse
    -0.07
    POSITIVE LOGITS
     برا
    0.09
     exaggerated
    0.08
     Vor
    0.08
     المطر
    0.07
     '
    ↵
    0.07
     armored
    0.07
     Guard
    0.07
    érico
    0.07
    Advisor
    0.07
     ਬਣ
    0.07
    Activations Density 0.004%

    No Known Activations