© 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. 7-RESID-POST-AA
    11. 851
    Prev
    Next
    INDEX
    Explanations

    uter

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     proficiency
    -0.08
     GUID
    -0.08
     verificar
    -0.08
     combinar
    -0.07
    精
    -0.07
    Combine
    -0.07
     basketball
    -0.07
     cabins
    -0.07
    -साथ
    -0.07
    বর
    -0.07
    POSITIVE LOGITS
    vum
    0.08
     felicidad
    0.08
    succ
    0.08
    íme
    0.07
     écr
    0.07
    .cover
    0.07
    ouveau
    0.07
     suelo
    0.07
    attanooga
    0.07
     sawa
    0.07
    Activations Density 0.000%

    No Known Activations