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. 119684
    Prev
    Next
    INDEX
    Explanations

    plus symbol

    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
     Col
    -0.08
     Peel
    -0.08
    (col
    -0.08
     कर्म
    -0.07
    _col
    -0.07
     পর
    -0.07
     Little
    -0.07
    Col
    -0.07
     saat
    -0.07
     עוד
    -0.07
    POSITIVE LOGITS
     regained
    0.10
    腾讯
    0.09
     rubble
    0.08
    Оп
    0.08
    pots
    0.08
     regain
    0.08
     antid
    0.08
    zust
    0.08
     nevertheless
    0.08
     sév
    0.08
    Activations Density 0.063%

    No Known Activations