Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 53227
    Prev
    Next
    INDEX
    Explanations

    Events and occurrences

    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
    Я
    -0.08
    thead
    -0.08
    Revision
    -0.07
     сказать
    -0.07
     Lazar
    -0.07
     intending
    -0.07
    STER
    -0.07
    apore
    -0.07
    K
    -0.07
     dryer
    -0.07
    POSITIVE LOGITS
     arbit
    0.09
     والمت
    0.09
     dintre
    0.08
     decorr
    0.08
     bhaineann
    0.08
    टल
    0.08
     somme
    0.08
     accompanies
    0.08
     sommet
    0.08
     torno
    0.08
    Activations Density 0.250%

    No Known Activations