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. 54254
    Prev
    Next
    INDEX
    Explanations

    phones

    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
     jurisdiction
    -0.09
    ishment
    -0.08
     ignorant
    -0.08
     census
    -0.07
     mutable
    -0.07
     election
    -0.07
     declarations
    -0.07
     nouveau
    -0.07
     lump
    -0.07
     arrec
    -0.07
    POSITIVE LOGITS
     headphones
    0.13
     headphone
    0.10
    监听
    0.10
     earbuds
    0.09
     multit
    0.09
    佩
    0.09
     geeignet
    0.08
    .listener
    0.08
     luisteren
    0.08
    戴
    0.08
    Activations Density 0.004%

    No Known Activations