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. 44234
    Prev
    Next
    INDEX
    Explanations

    Questions and uncertainty

    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
    barra
    -0.08
    oller
    -0.08
    issi
    -0.08
    aim
    -0.08
    prima
    -0.08
     aiming
    -0.08
     olen
    -0.08
    unang
    -0.08
    wh
    -0.08
    upos
    -0.08
    POSITIVE LOGITS
     trajectories
    0.09
     Forgotten
    0.08
     countless
    0.08
    ://${
    0.08
     RU
    0.08
     fleeting
    0.08
     مستقبل
    0.08
     migliori
    0.08
     insanların
    0.08
     सर्वो
    0.08
    Activations Density 0.056%

    No Known Activations