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. 54364
    Prev
    Next
    INDEX
    Explanations

    period

    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
    amarca
    -0.08
     mens
    -0.08
     Freud
    -0.07
    nými
    -0.07
     confirms
    -0.07
    té
    -0.07
    ným
    -0.07
     financially
    -0.07
     distributions
    -0.07
     frequentemente
    -0.07
    POSITIVE LOGITS
    かわ
    0.07
     😊
    0.07
    "errors
    0.07
     уст
    0.07
    'en
    0.07
     Rever
    0.07
    ริ่ม
    0.07
    Verse
    0.07
    ’en
    0.07
     לכל
    0.07
    Activations Density 0.054%

    No Known Activations