© 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. 96778
    Prev
    Next
    INDEX
    Explanations

    Spanish language

    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
     tragam
    -0.11
     apporte
    -0.11
     limité
    -0.11
     kiest
    -0.10
     toqu
    -0.10
     toont
    -0.10
     utk
    -0.10
     élev
    -0.10
     lern
    -0.10
     mostram
    -0.10
    POSITIVE LOGITS
    adece
    0.14
    uerda
    0.11
    aza
    0.11
    arece
    0.11
    ende
    0.11
    arca
    0.11
    ita
    0.10
    aga
    0.10
    ande
    0.10
    prime
    0.10
    Activations Density 0.012%

    No Known Activations