© 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. 11-RESID-POST-AA
    11. 55
    Prev
    Next
    INDEX
    Explanations

    focal

    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
     inequalities
    -0.08
    Sal
    -0.07
    -0.07
    _probs
    -0.07
    वा
    -0.07
    PRECATED
    -0.07
    ലെ
    -0.07
    _except
    -0.07
     Maz
    -0.07
    -heavy
    -0.07
    POSITIVE LOGITS
     быстр
    0.09
    arada
    0.08
     фирмы
    0.08
    יקס
    0.08
    imet
    0.08
     бума
    0.08
     крат
    0.08
    .bumptech
    0.08
     metre
    0.08
     personnels
    0.08
    Activations Density 0.002%
    No Known Activations