© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 23-RESID-POST-AA
    11. 47621
    Prev
    Next
    INDEX
    Explanations

    Studio

    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
    ings
    -0.12
    itudes
    -0.10
    stakes
    -0.10
    stellen
    -0.09
    stad
    -0.09
    stone
    -0.09
    stoffe
    -0.09
    stenen
    -0.09
    stones
    -0.09
    steigen
    -0.09
    POSITIVE LOGITS
     звук
    0.12
     apartment
    0.10
    録
    0.10
    棚
    0.09
    .photos
    0.09
     portraits
    0.09
    录
    0.09
     recordings
    0.09
     session
    0.09
    -generated
    0.09
    Activations Density 0.006%

    No Known Activations