© 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. 102801
    Prev
    Next
    INDEX
    Explanations

    formatting

    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
    upakan
    -0.08
    668
    -0.08
     얻
    -0.08
     tästä
    -0.08
     کاهش
    -0.07
     وتق
    -0.07
    archives
    -0.07
    743
    -0.07
     사업
    -0.07
    038
    -0.07
    POSITIVE LOGITS
     formatted
    0.19
     phr
    0.18
    格式
    0.17
     phrase
    0.17
     format
    0.17
     wording
    0.16
    formatted
    0.16
     formatting
    0.16
    Formatted
    0.15
     формат
    0.15
    Activations Density 0.054%

    No Known Activations