© 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. 11-RESID-POST-AA
    11. 94597
    Prev
    Next
    INDEX
    Explanations

    (

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nějak
    -0.09
    些
    -0.08
     ਕਿਸ
    -0.08
    形式
    -0.08
     দক্ষ
    -0.08
     ਜਾਣ
    -0.08
    一些
    -0.08
     które
    -0.08
     ਕ
    -0.08
     cues
    -0.08
    POSITIVE LOGITS
    Cannot
    0.09
    must
    0.08
    argument
    0.08
     inherent
    0.08
     Cannot
    0.08
     cannot
    0.08
    cannot
    0.08
     must
    0.08
     imperative
    0.07
    abaa
    0.07
    Activations Density 0.004%

    No Known Activations