© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 102124
    Prev
    Next
    INDEX
    Explanations

    :

    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
    其他
    -0.11
     басқа
    -0.10
     неш
    -0.10
    各种
    -0.10
     other
    -0.10
    aditional
    -0.10
    하지만
    -0.10
    ,etc
    -0.09
     outras
    -0.09
     άλλ
    -0.09
    POSITIVE LOGITS
     Consider
    0.21
     consider
    0.19
    Consider
    0.19
     considerar
    0.15
     Define
    0.15
     considère
    0.15
     consid
    0.15
     considera
    0.14
    Define
    0.14
    consider
    0.14
    Activations Density 0.028%

    No Known Activations