© 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. 96724
    Prev
    Next
    INDEX
    Explanations

    Gew

    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
    sery
    -0.08
     قي
    -0.08
    cem
    -0.08
     represent
    -0.07
    컵
    -0.07
     facer
    -0.07
    ಸಿ
    -0.07
     ukuf
    -0.07
    ซี
    -0.07
    ^{
    -0.07
    POSITIVE LOGITS
    alaho
    0.13
    inna
    0.11
    inner
    0.11
    inn
    0.10
    alui
    0.10
    intern
    0.10
    ार
    0.10
    bodaeth
    0.10
    ijzig
    0.10
    ohnt
    0.10
    Activations Density 0.004%

    No Known Activations