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. 101577
    Prev
    Next
    INDEX
    Explanations

    numbers

    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
     lan
    -0.07
    िले
    -0.07
     locom
    -0.07
     voltar
    -0.07
     fly
    -0.07
     rb
    -0.07
     walk
    -0.07
     Grid
    -0.07
     ru
    -0.07
    -wave
    -0.07
    POSITIVE LOGITS
    Philip
    0.09
     аромат
    0.09
     жид
    0.09
    Chu
    0.08
     salts
    0.08
     Bosnia
    0.08
    шыя
    0.08
    African
    0.08
    Oil
    0.08
     ശ്രീ
    0.07
    Activations Density 2.323%

    No Known Activations