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. 44695
    Prev
    Next
    INDEX
    Explanations

    restart

    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
    mills
    -0.09
    双色球
    -0.08
     wb
    -0.08
     Mw
    -0.08
     Tripadvisor
    -0.08
     Coupons
    -0.08
     Bw
    -0.08
     தலைம
    -0.08
    @interface
    -0.08
    ?w
    -0.08
    POSITIVE LOGITS
    机制
    0.09
    "]))↵
    0.08
    ")))↵
    0.08
    "))↵
    0.08
    'économie
    0.08
    anges
    0.08
    "]),↵
    0.07
    ૈ
    0.07
    ']))↵
    0.07
    _mean
    0.07
    Activations Density 0.000%

    No Known Activations