© 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. 23-RESID-POST-AA
    11. 48026
    Prev
    Next
    INDEX
    Explanations

    French language texts

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    *T
    -0.09
     “
    -0.08
     diversité
    -0.08
    യില്
    -0.08
     allocation
    -0.08
     Allocation
    -0.08
    Ծ
    -0.07
     koʻ
    -0.07
     synchronization
    -0.07
     chaînes
    -0.07
    POSITIVE LOGITS
    'hui
    0.14
    aremment
    0.11
    'espère
    0.11
     ?↵↵
    0.10
    'était
    0.10
    'elle
    0.10
    'avez
    0.10
    'à
    0.10
    teresse
    0.10
    éralement
    0.10
    Activations Density 0.060%

    No Known Activations