© 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. 11-RESID-POST-AA
    11. 70850
    Prev
    Next
    INDEX
    Explanations

    written documents

    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
    �
    -0.08
    يسي
    -0.08
     onderste
    -0.07
     enriched
    -0.07
     debat
    -0.07
     EH
    -0.07
     figure
    -0.07
     invoice
    -0.07
    -0.07
     predicate
    -0.07
    POSITIVE LOGITS
    -là
    0.10
     keer
    0.09
    Tho
    0.09
     Gaga
    0.08
    &o
    0.08
    ికి
    0.08
    alue
    0.08
     varten
    0.08
     iff
    0.08
     અંગ
    0.08
    Activations Density 0.121%
    No Known Activations