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. 44245
    Prev
    Next
    INDEX
    Explanations

    zero

    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
    MON
    -0.09
     Horizon
    -0.08
    mon
    -0.08
     hét
    -0.08
     Coordination
    -0.08
    ruč
    -0.08
     Age
    -0.08
    oula
    -0.08
     coordinator
    -0.07
     Rate
    -0.07
    POSITIVE LOGITS
     ഭാഗ
    0.10
     തീ
    0.09
     آب
    0.09
     ഞാൻ
    0.09
     dostęp
    0.08
    ,比如
    0.08
     നിങ്ങൾ
    0.08
     ലഭ
    0.08
     അല്ല
    0.08
     തയ്യാറ
    0.08
    Activations Density 0.015%

    No Known Activations