© 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. 23-RESID-POST-AA
    11. 51713
    Prev
    Next
    INDEX
    Explanations

    say "apanese"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     aig
    -0.09
     Fais
    -0.08
    (argument
    -0.08
     Pet
    -0.08
    cream
    -0.08
     Tus
    -0.07
    ped
    -0.07
    pet
    -0.07
     төмен
    -0.07
     eyeb
    -0.07
    POSITIVE LOGITS
    .DE
    0.08
     gezellige
    0.08
     partitions
    0.07
     وا
    0.07
    Italic
    0.07
     idag
    0.07
    0.07
    Qua
    0.07
    Partition
    0.07
    నలు
    0.07
    Activations Density 0.000%
    No Known Activations