© 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. 20927
    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
     as
    -0.10
     considerable
    -0.08
     including
    -0.08
     in
    -0.08
     😀↵↵
    -0.08
     on
    -0.08
     for
    -0.08
     reaching
    -0.08
     pending
    -0.07
     focusing
    -0.07
    POSITIVE LOGITS
     ancient
    0.13
    ampunk
    0.13
     medieval
    0.12
     القديم
    0.12
     древ
    0.12
     Medieval
    0.12
    古
    0.12
    废
    0.11
     futuristic
    0.11
     melanch
    0.11
    Activations Density 0.010%

    No Known Activations