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. 53224
    Prev
    Next
    INDEX
    Explanations

    Negation

    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
     virtue
    -0.08
     WB
    -0.08
     trou
    -0.08
    ख
    -0.07
     làm
    -0.07
     bol
    -0.07
    htt
    -0.07
    增强
    -0.07
     já
    -0.07
    充
    -0.07
    POSITIVE LOGITS
     implying
    0.10
     seng
    0.08
     ari
    0.07
    掉
    0.07
     hur
    0.07
     سوى
    0.07
     Toon
    0.07
     terlalu
    0.07
     Nr
    0.07
    paced
    0.07
    Activations Density 0.140%

    No Known Activations