© 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. 102725
    Prev
    Next
    INDEX
    Explanations

    comma

    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
    :↵
    -0.08
    |
    -0.08
    ನಿ
    -0.07
    ><
    -0.07
    :
    -0.07
    നും
    -0.07
    >|
    -0.07
    Instead
    -0.07
    ){
    -0.07
    >K
    -0.06
    POSITIVE LOGITS
     overall
    0.16
     その他
    0.16
     Overall
    0.16
    その他
    0.16
    Overall
    0.15
     অন্যান্য
    0.15
     insgesamt
    0.14
    overall
    0.14
    整体
    0.14
     기타
    0.13
    Activations Density 0.079%

    No Known Activations