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. 56263
    Prev
    Next
    INDEX
    Explanations

    Code examples

    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
     volver
    -0.08
     violent
    -0.08
     censor
    -0.07
     seizure
    -0.07
     audits
    -0.07
    ERP
    -0.07
     povo
    -0.07
    -0.07
     insomnia
    -0.07
    BUG
    -0.07
    POSITIVE LOGITS
     prevailed
    0.09
    academ
    0.08
    xampp
    0.08
    _Msp
    0.08
    -specific
    0.08
     madura
    0.07
    198
    0.07
    _ln
    0.07
    neutral
    0.07
    тык
    0.07
    Activations Density 0.004%

    No Known Activations