© 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. 97404
    Prev
    Next
    INDEX
    Explanations

    "to be"

    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
     daha
    -0.08
     подробнее
    -0.08
     interesantes
    -0.08
     летом
    -0.08
     roomy
    -0.08
     possibles
    -0.07
    -point
    -0.07
     lofty
    -0.07
     Déc
    -0.07
     więks
    -0.07
    POSITIVE LOGITS
     unavoidable
    0.20
     acceptable
    0.17
     inevitable
    0.15
     tolerated
    0.15
     indispensable
    0.15
     imprescindible
    0.14
     accepted
    0.14
     permitido
    0.14
     exempt
    0.14
     permitted
    0.14
    Activations Density 0.011%

    No Known Activations