© 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. 94842
    Prev
    Next
    INDEX
    Explanations

    bullet point lists

    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
    ，而且
    -0.08
    payer
    -0.08
     interm
    -0.08
    	fi
    -0.08
    �
    -0.07
     payday
    -0.07
    ILENAME
    -0.07
    ாமல்
    -0.07
    Temp
    -0.07
    intl
    -0.07
    POSITIVE LOGITS
     Lastly
    0.12
     Finally
    0.11
    Lastly
    0.10
     Enfin
    0.10
     lastly
    0.09
     schließlich
    0.09
    Finally
    0.09
     finally
    0.09
    —all
    0.09
     Finalmente
    0.09
    Activations Density 0.678%

    No Known Activations