© 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. 23-RESID-POST-AA
    11. 6057
    Prev
    Next
    INDEX
    Explanations

    G

    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
     թեմ
    -0.08
     బయ
    -0.08
     շրջանակ
    -0.08
    ācija
    -0.08
     ფარგლებში
    -0.08
     manhã
    -0.08
    massa
    -0.08
    ემბ
    -0.08
     մարտ
    -0.08
     gotas
    -0.08
    POSITIVE LOGITS
    owan
    0.16
    inniss
    0.13
    wire
    0.12
    urk
    0.12
    uff
    0.12
    raw
    0.11
    hee
    0.11
    inty
    0.11
    uint
    0.11
    rail
    0.11
    Activations Density 0.001%

    No Known Activations