© 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 EvalsExportsAPI 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. 20614
    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
    imal
    -0.10
    ,
    -0.09
    illah
    -0.09
     manner
    -0.08
    ound
    -0.08
    ounded
    -0.08
    ipped
    -0.08
    これは
    -0.08
    ufficient
    -0.08
    quial
    -0.08
    POSITIVE LOGITS
     justement
    0.13
     précisément
    0.12
     precisely
    0.11
     gdje
    0.11
     where
    0.11
    ենց
    0.11
     upravo
    0.11
    	where
    0.11
     Exactly
    0.10
     որտեղ
    0.10
    Activations Density 0.005%

    No Known Activations