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. 58312
    Prev
    Next
    INDEX
    Explanations

    Network bridging

    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
     Tolkien
    -0.09
     Sant
    -0.09
     brilliant
    -0.08
    fas
    -0.08
    ଥ
    -0.08
    avers
    -0.08
    descending
    -0.08
    Fear
    -0.08
    HU
    -0.08
     Anglo
    -0.07
    POSITIVE LOGITS
    组
    0.09
    石
    0.08
     coi
    0.08
    ивал
    0.07
    cors
    0.07
    静
    0.07
     dew
    0.07
     chill
    0.07
     Stunden
    0.07
     yt
    0.07
    Activations Density 0.003%

    No Known Activations