© 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. 78786
    Prev
    Next
    INDEX
    Explanations

    reading user input

    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
     unlike
    -0.09
    Unlike
    -0.09
    Compared
    -0.08
     Unlike
    -0.08
     Dar
    -0.08
     contrairement
    -0.08
    不像
    -0.08
    -0.07
    @Configuration
    -0.07
     lemb
    -0.07
    POSITIVE LOGITS
    Fallback
    0.10
     fallback
    0.09
    fallback
    0.09
     comunque
    0.09
    allback
    0.09
    _default
    0.08
     самостоятельно
    0.08
     подраз
    0.08
    	default
    0.08
    achaidh
    0.08
    Activations Density 0.017%
    No Known Activations