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. 119444
    Prev
    Next
    INDEX
    Explanations

    SQL parameter binding

    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
     fract
    -0.09
     domin
    -0.08
     éve
    -0.08
     江
    -0.08
    δρο
    -0.08
     selfish
    -0.08
     пре
    -0.08
     supremacy
    -0.08
     ego
    -0.08
     levy
    -0.08
    POSITIVE LOGITS
     pstmt
    0.11
    插
    0.11
     INSERT
    0.10
     injection
    0.10
     injections
    0.09
     bindings
    0.09
     Prepared
    0.09
    	Prepared
    0.09
     PDO
    0.09
     injectable
    0.09
    Activations Density 0.003%

    No Known Activations