© 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. 715
    Prev
    Next
    INDEX
    Explanations

    reimbursement

    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
     Eid
    -0.08
     nouveau
    -0.07
    .nick
    -0.07
     Dol
    -0.07
    род
    -0.07
    ją
    -0.07
    -crafted
    -0.07
     reside
    -0.07
    പ്പോ
    -0.07
     bebé
    -0.07
    POSITIVE LOGITS
     reimb
    0.09
    .hk
    0.09
     reimburse
    0.09
    (/
    0.08
     reimbursement
    0.08
    uest
    0.08
     पाने
    0.08
    _BATCH
    0.08
     ¥
    0.07
     blanch
    0.07
    Activations Density 0.004%

    No Known Activations