© 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. 15-RESID-POST-AA
    11. 16575
    Prev
    Next
    INDEX
    Explanations

    memory

    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_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _packages
    -0.08
    /package
    -0.08
    .flag
    -0.08
     brutality
    -0.08
     सौ
    -0.08
    .package
    -0.08
     violencia
    -0.08
    antiated
    -0.08
    (pkg
    -0.08
     Umb
    -0.08
    POSITIVE LOGITS
     hippoc
    0.14
    (memory
    0.13
    .memory
    0.13
     memory
    0.13
     geheugen
    0.13
     памяти
    0.12
     Memory
    0.12
    .Memory
    0.12
     memória
    0.12
     memoria
    0.12
    Activations Density 0.008%

    No Known Activations