© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 78847
    Prev
    Next
    INDEX
    Explanations

    locked

    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
     mindfulness
    -0.09
    [count
    -0.08
     полно
    -0.08
     числа
    -0.08
     풍
    -0.07
     pairing
    -0.07
     WATER
    -0.07
     wood
    -0.07
     количе
    -0.07
     крем
    -0.07
    POSITIVE LOGITS
     tijdelijk
    0.10
     automatiquement
    0.10
    账户
    0.10
     tempora
    0.10
     temporarily
    0.10
    temporary
    0.09
     permanently
    0.09
    狠狠
    0.09
     akun
    0.09
    Temporary
    0.09
    Activations Density 0.011%

    No Known Activations