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. 43114
    Prev
    Next
    INDEX
    Explanations

    Language usage and definition

    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
    774
    -0.08
    -phase
    -0.08
     Пост
    -0.08
    784
    -0.08
     Dress
    -0.08
     Мен
    -0.08
    Languages
    -0.08
    лежащ
    -0.08
    рус
    -0.07
     Seam
    -0.07
    POSITIVE LOGITS
     slang
    0.10
    表示
    0.10
     unfair
    0.09
     shorthand
    0.09
    意味
    0.09
    暗
    0.09
     derog
    0.09
    恶
    0.09
    用于
    0.09
     trolling
    0.09
    Activations Density 0.028%

    No Known Activations