© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 103096
    Prev
    Next
    INDEX
    Explanations

    this

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ings
    -0.14
    <|reserved_200000|>
    -0.12
    this
    -0.12
    these
    -0.12
    <|reserved_200014|>
    -0.12
    ‌లు
    -0.12
    gages
    -0.12
    ्स
    -0.11
    ments
    -0.11
    ഈ
    -0.11
    POSITIVE LOGITS
     is
    0.21
     particular
    0.20
     nedenle
    0.17
     kind
    0.15
     latter
    0.14
     entire
    0.14
     yüzden
    0.14
     way
    0.14
     ধরনের
    0.13
     durumda
    0.13
    Activations Density 0.293%

    No Known Activations