© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 22151
    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
    ।↵↵
    -0.11
    ையை
    -0.11
     =↵
    -0.11
    த்தை
    -0.10
    	this
    -0.10
    )에
    -0.10
    তা
    -0.10
    =this
    -0.10
    ,在
    -0.09
    ਤਾ
    -0.09
    POSITIVE LOGITS
    -made
    0.12
    -lasting
    0.12
    -fledged
    0.12
    -going
    0.12
    -away
    0.12
    -handed
    0.11
    -out
    0.11
    -lived
    0.11
    -fashioned
    0.11
    -hearted
    0.11
    Activations Density 0.097%

    No Known Activations