© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 129448
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
    осуд
    -0.08
    		↵		↵		↵
    -0.08
     തന്ന
    -0.08
    		
↵		
↵
    -0.07
    -0.07
     بسبب
    -0.07
    ERG
    -0.07
    مط
    -0.07
     اقدامات
    -0.07
    infra
    -0.07
    POSITIVE LOGITS
    后的
    0.10
     finais
    0.09
     thereafter
    0.08
    -final
    0.08
    之后
    0.08
    账
    0.08
    河北
    0.08
     ситуацию
    0.08
     daa
    0.08
     anschließend
    0.08
    Activations Density 0.071%
    No Known Activations