© 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. 102361
    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
    ちなみに
    -0.09
    ownika
    -0.08
    િસ
    -0.08
    իս
    -0.08
     surpre
    -0.08
     سامنے
    -0.08
    umbersome
    -0.08
     donnant
    -0.08
     démarches
    -0.08
    ပ်
    -0.08
    POSITIVE LOGITS
     unless
    0.17
    Unless
    0.17
     Unless
    0.16
     Therefore
    0.16
     must
    0.16
     therefore
    0.16
    Therefore
    0.15
    unless
    0.15
    必须
    0.14
     daarom
    0.14
    Activations Density 0.052%

    No Known Activations