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. 54288
    Prev
    Next
    INDEX
    Explanations

    alternate

    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
     attended
    -0.10
     attending
    -0.09
     참석
    -0.08
    .–
    -0.08
    /items
    -0.07
     storing
    -0.07
     passing
    -0.07
     attend
    -0.07
     attendance
    -0.07
    Attend
    -0.07
    POSITIVE LOGITS
     fiction
    0.10
    -fiction
    0.09
    fiction
    0.09
     fantasy
    0.08
     worlds
    0.08
     fantast
    0.08
    ubi
    0.08
     ficción
    0.08
     Worlds
    0.08
     fictional
    0.08
    Activations Density 0.006%

    No Known Activations