© 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. 102703
    Prev
    Next
    INDEX
    Explanations

    computer code

    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
     atau
    -0.11
     oder
    -0.11
    或
    -0.11
     বা
    -0.10
     或
    -0.10
     hoặc
    -0.10
     или
    -0.10
    或者
    -0.10
     yoki
    -0.09
     లేదా
    -0.09
    POSITIVE LOGITS
     uitdagingen
    0.09
     гаст
    0.09
    ئلة
    0.08
     excluir
    0.08
    CLUDING
    0.08
     fordert
    0.08
     भोजन
    0.08
     excerpts
    0.08
     Gameplay
    0.08
     exclusions
    0.08
    Activations Density 0.000%

    No Known Activations