Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 19523
    Prev
    Next
    INDEX
    Explanations

    >"

    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_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ORLD
    -0.08
    ESA
    -0.08
    跑路
    -0.08
     WORLD
    -0.08
     yrs
    -0.08
     trafficking
    -0.08
    Drops
    -0.07
    zira
    -0.07
     bardziej
    -0.07
    txn
    -0.07
    POSITIVE LOGITS
     television
    0.09
     televisions
    0.08
     evolve
    0.08
    .Temp
    0.07
    .Attribute
    0.07
    .Subject
    0.07
     ammonia
    0.07
    /change
    0.07
    P
    0.07
     entz
    0.07
    Activations Density 0.000%

    No Known Activations