© 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. 48021
    Prev
    Next
    INDEX
    Explanations

    client

    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
     reputation
    -0.07
     dubb
    -0.07
     freedom
    -0.07
     deadline
    -0.07
     scarcity
    -0.07
     resh
    -0.07
     liber
    -0.07
     avr
    -0.07
    と言
    -0.07
     реп
    -0.07
    POSITIVE LOGITS
    istisch
    0.09
    -total
    0.08
    istent
    0.08
    测
    0.08
    _total
    0.08
    isable
    0.08
     případ
    0.07
     punched
    0.07
    >Select
    0.07
     Chesapeake
    0.07
    Activations Density 0.001%

    No Known Activations