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. 58404
    Prev
    Next
    INDEX
    Explanations

    fox

    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
     pasangan
    -0.08
    kow
    -0.07
    IDL
    -0.07
     identify
    -0.07
     indicating
    -0.07
    venue
    -0.07
     graphs
    -0.07
    -0.07
     sickness
    -0.07
     indicative
    -0.07
    POSITIVE LOGITS
     fox
    0.10
    狐狸
    0.08
    es
    0.08
     cunning
    0.08
     Sets
    0.08
    soz
    0.08
    fox
    0.08
     Lyn
    0.08
     brightly
    0.07
     domést
    0.07
    Activations Density 0.004%

    No Known Activations