© 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. 103071
    Prev
    Next
    INDEX
    Explanations

    Verify

    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
     besloten
    -0.09
     dependiendo
    -0.09
    ‍ന്ന്
    -0.09
    -delà
    -0.08
     ondernemen
    -0.08
     tenzij
    -0.08
     istället
    -0.08
     décidé
    -0.08
    这里只有
    -0.08
    ’importe
    -0.08
    POSITIVE LOGITS
    验证
    0.24
    .verify
    0.23
     verify
    0.22
    verify
    0.22
    Verify
    0.22
     Verify
    0.22
     verifying
    0.22
    _verify
    0.21
     verifies
    0.21
    .validate
    0.21
    Activations Density 0.095%

    No Known Activations