© 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. 11-RESID-POST-AA
    11. 25195
    Prev
    Next
    INDEX
    Explanations

    code

    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
     philosoph
    -0.10
    -existent
    -0.09
    _fixture
    -0.09
     filos
    -0.09
     favoris
    -0.08
     filosof
    -0.08
     Fazenda
    -0.08
    ystate
    -0.08
    htable
    -0.08
     primas
    -0.08
    POSITIVE LOGITS
     assistance
    0.10
    金
    0.08
     Assistance
    0.07
     സഹായ
    0.07
    .help
    0.07
     guidance
    0.07
     helps
    0.07
     membantu
    0.07
     problemer
    0.07
     помощь
    0.07
    Activations Density 0.005%

    No Known Activations