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. 65772
    Prev
    Next
    INDEX
    Explanations

    Math/Logic problems

    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
     Nitro
    -0.08
    emos
    -0.08
     Nelson
    -0.07
     Tantra
    -0.07
    +B
    -0.07
     massac
    -0.07
     nitric
    -0.07
     Navarro
    -0.07
    나
    -0.07
     zehn
    -0.07
    POSITIVE LOGITS
    ખ
    0.08
    час
    0.07
     iştirak
    0.07
     MISS
    0.07
     boob
    0.07
    дәк
    0.07
     soup
    0.07
     wholly
    0.07
    Α
    0.07
     undue
    0.07
    Activations Density 0.254%

    No Known Activations