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. 11-RESID-POST-AA
    6. 109839
    Prev
    Next
    INDEX
    Explanations

    )

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     предст
    -0.09
    orme
    -0.09
     Donald
    -0.08
     Eug
    -0.08
     sunk
    -0.08
     chce
    -0.08
     Carnegie
    -0.08
    AKE
    -0.08
     dur
    -0.07
     Mohamed
    -0.07
    POSITIVE LOGITS
    Convers
    0.09
     casar
    0.08
    Therefore
    0.08
    like
    0.07
     SAD
    0.07
    ledger
    0.07
    Usually
    0.07
     whereas
    0.07
    That's
    0.07
     SPO
    0.07
    Activations Density 0.027%

    No Known Activations