© 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. 102939
    Prev
    Next
    INDEX
    Explanations

    mathematical proofs

    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
    ‍:
    -0.11
     standout
    -0.11
    ：https
    -0.10
     fallback
    -0.09
     teal
    -0.09
     الـ
    -0.09
    ‌
    -0.09
     �
    -0.09
     impactful
    -0.09
    ഴ്
    -0.09
    POSITIVE LOGITS
    ----------------------------------------------------------------
    0.13
     moreover
    0.13
     daß
    0.13
     muß
    0.12
     furthermore
    0.12
     Moreover
    0.11
     Furthermore
    0.11
     realise
    0.11
     indispens
    0.11
     everybody
    0.10
    Activations Density 0.036%

    No Known Activations