© 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. 19-RESID-POST-AA
    11. 102785
    Prev
    Next
    INDEX
    Explanations

    ban

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     humild
    -0.08
    亏
    -0.08
     autent
    -0.07
    -0.07
    _spacing
    -0.07
    ộn
    -0.07
     alright
    -0.07
     homens
    -0.07
     menghasilkan
    -0.07
     ahaan
    -0.07
    POSITIVE LOGITS
    াদেশ
    0.15
     imposed
    0.14
    /block
    0.14
    措施
    0.13
     Enforcement
    0.12
     enforced
    0.12
    解除
    0.12
     enacted
    0.11
     periods
    0.11
     enforcement
    0.11
    Activations Density 0.075%
    No Known Activations