© 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. 11-RESID-POST-AA
    11. 69695
    Prev
    Next
    INDEX
    Explanations

    Sopranos or writing structures

    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
     nagh
    -0.09
     kama
    -0.08
     ph
    -0.08
     nina
    -0.08
     saff
    -0.08
     tey
    -0.08
     dikkat
    -0.08
     چي
    -0.08
     sega
    -0.08
     kuk
    -0.08
    POSITIVE LOGITS
    ließ
    0.07
     surprises
    0.07
    icking
    0.07
    427
    0.07
     iniciativas
    0.07
     todos
    0.07
     Forgotten
    0.07
    untos
    0.07
     tutti
    0.07
    545
    0.07
    Activations Density 0.001%

    No Known Activations