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. 112833
    Prev
    Next
    INDEX
    Explanations

    rim

    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
     cler
    -0.07
     ambas
    -0.07
     mód
    -0.07
    adow
    -0.07
     Kirby
    -0.07
     Hep
    -0.07
     fec
    -0.07
     fel
    -0.07
    (Collectors
    -0.07
     saliva
    -0.07
    POSITIVE LOGITS
     blurry
    0.09
    顶部
    0.08
     shut
    0.08
     haze
    0.08
     Inflate
    0.08
    isem
    0.07
     Horizonte
    0.07
     मंद
    0.07
     rundt
    0.07
     oluş
    0.07
    Activations Density 0.003%

    No Known Activations