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. 7-RESID-POST-AA
    6. 1884
    Prev
    Next
    INDEX
    Explanations

    frustration

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ropa
    -0.08
     baptized
    -0.08
    -Lo
    -0.08
     Cumberland
    -0.08
    Ru
    -0.08
    RU
    -0.07
    tails
    -0.07
     Hanover
    -0.07
    문
    -0.07
    UICollection
    -0.07
    POSITIVE LOGITS
     ters
    0.09
    -vous
    0.08
     VE
    0.08
     Ι
    0.08
    ाजन
    0.08
     frustrating
    0.08
     understandably
    0.08
     frustrations
    0.07
    程度
    0.07
    .builders
    0.07
    Activations Density 0.006%

    No Known Activations