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. 44241
    Prev
    Next
    INDEX
    Explanations

    statement

    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
    }`}>↵
    -0.08
    También
    -0.08
    }.↵
    -0.08
    ают
    -0.07
    <V
    -0.07
    -нибудь
    -0.07
    }}>↵
    -0.07
    };↵↵//
    -0.07
     thrives
    -0.07
    ृष
    -0.07
    POSITIVE LOGITS
     العلاقة
    0.09
    เส
    0.09
     الوضع
    0.09
     ":"
    0.08
     কে
    0.08
     Gregg
    0.08
     প্রকাশ
    0.08
     waive
    0.08
     purported
    0.08
     genie
    0.08
    Activations Density 0.029%

    No Known Activations