© 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. 6341
    Prev
    Next
    INDEX
    Explanations

    corresponds

    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
     گذا
    -0.08
     చేసి
    -0.08
     kõik
    -0.07
     ప్రకట
    -0.07
    agdagan
    -0.07
    emene
    -0.07
     kokku
    -0.07
     konke
    -0.07
    �్య
    -0.07
    asley
    -0.07
    POSITIVE LOGITS
     corresponds
    0.61
     corresponding
    0.56
     Correspond
    0.54
    Correspond
    0.54
    对应
    0.53
     correspond
    0.52
     correspondente
    0.49
     correspondant
    0.49
     corresponde
    0.47
     correspondientes
    0.45
    Activations Density 0.717%

    No Known Activations