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. 45336
    Prev
    Next
    INDEX
    Explanations

    Math/Computer science problems

    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
     hul
    -0.08
     Kas
    -0.08
    Kas
    -0.07
     forage
    -0.07
     Keep
    -0.07
    Keep
    -0.07
     Paula
    -0.07
    Hun
    -0.07
    keep
    -0.07
    'il
    -0.07
    POSITIVE LOGITS
     Worst
    0.12
     worst
    0.11
    Worst
    0.10
     berubah
    0.09
    wor
    0.09
     propriétaires
    0.08
    еді
    0.08
    _best
    0.08
     সবচ
    0.08
     toughest
    0.08
    Activations Density 0.045%

    No Known Activations