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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 21979
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    HELP
    -0.08
    르고
    -0.08
    ARTICLE
    -0.08
    	User
    -0.08
    .Now
    -0.08
    	Product
    -0.07
    OTP
    -0.07
    	Ext
    -0.07
    	URL
    -0.07
    	Message
    -0.07
    POSITIVE LOGITS
    ))
    0.09
    alyzed
    0.09
    ))).
    0.09
    }.
    0.08
    esha
    0.08
    alyze
    0.08
     flere
    0.08
    }`,
    0.08
    .enabled
    0.08
    aly
    0.08
    Activations Density 0.007%

    No Known Activations