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. 30479
    Prev
    Next
    INDEX
    Explanations

    days and holidays

    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
     specialising
    -0.08
     tube
    -0.08
    əl
    -0.07
    esis
    -0.07
    ircle
    -0.07
    igeze
    -0.07
     filament
    -0.07
    _argument
    -0.07
    amag
    -0.07
    angelo
    -0.07
    POSITIVE LOGITS
     consecut
    0.10
     компенса
    0.10
     подряд
    0.10
     компен
    0.09
     quarantine
    0.09
     consecutive
    0.09
     Conse
    0.09
     getaway
    0.09
     vacation
    0.09
     lễ
    0.09
    Activations Density 0.011%

    No Known Activations