© 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 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. 69147
    Prev
    Next
    INDEX
    Explanations

    Effect/outcome

    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
    弄
    -0.08
     invading
    -0.08
     sekal
    -0.08
    INV
    -0.07
     Entries
    -0.07
     Kasino
    -0.07
     Alvin
    -0.07
    waga
    -0.07
    castle
    -0.07
    inv
    -0.07
    POSITIVE LOGITS
     benefícios
    0.10
     outcomes
    0.10
    成果
    0.09
     benefits
    0.09
    效果
    0.09
    Benefits
    0.09
     reception
    0.09
     hoped
    0.09
     testimonials
    0.09
    াফল
    0.09
    Activations Density 0.063%

    No Known Activations