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. 67213
    Prev
    Next
    INDEX
    Explanations

    timely

    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
    wür
    -0.08
     skriv
    -0.08
     Fahrenheit
    -0.08
    >S
    -0.08
    595
    -0.08
     genealogy
    -0.08
    /button
    -0.08
     Suk
    -0.08
    週間
    -0.07
     功
    -0.07
    POSITIVE LOGITS
     intangible
    0.09
     updates
    0.08
     timely
    0.08
     대응
    0.08
     своев
    0.08
     actuar
    0.07
     manner
    0.07
    _updates
    0.07
    DH
    0.07
    zeitig
    0.07
    Activations Density 0.008%

    No Known Activations