© 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. 5736
    Prev
    Next
    INDEX
    Explanations

    abstraction

    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
     инструкция
    -0.07
     assignments
    -0.07
    .JPG
    -0.07
    acre
    -0.07
     DTSTART
    -0.07
     ICO
    -0.07
     ASCII
    -0.07
     Guinness
    -0.07
     સૂચ
    -0.07
     Successfully
    -0.07
    POSITIVE LOGITS
     abstracts
    0.30
     encaps
    0.29
     abstract
    0.26
    abstract
    0.24
    封
    0.23
     abstraction
    0.23
    Abstract
    0.22
     abstra
    0.22
     Abstract
    0.22
     abstr
    0.21
    Activations Density 0.081%

    No Known Activations