© 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. 78910
    Prev
    Next
    INDEX
    Explanations

    stories

    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
    ’util
    -0.08
     originalmente
    -0.08
     имеется
    -0.08
     intervene
    -0.08
    'util
    -0.08
     específicamente
    -0.07
    owania
    -0.07
    .backends
    -0.07
     כלומר
    -0.07
     secondly
    -0.07
    POSITIVE LOGITS
    마다
    0.12
     сайын
    0.11
    累
    0.10
    越来越
    0.10
     accumulation
    0.10
     semakin
    0.10
    不断
    0.09
    积
    0.09
     cumul
    0.09
     વધારો
    0.09
    Activations Density 0.023%

    No Known Activations