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. 76338
    Prev
    Next
    INDEX
    Explanations

    TF

    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
     toes
    -0.09
     fundamentos
    -0.08
     പി
    -0.08
    adag
    -0.08
     jambes
    -0.08
     tendências
    -0.08
     Boilers
    -0.08
    atória
    -0.08
    ازد
    -0.08
     туралы
    -0.08
    POSITIVE LOGITS
    json
    0.09
    加载
    0.08
    .Animation
    0.08
    .voice
    0.08
    JSON
    0.08
    .json
    0.07
    Loader
    0.07
    (json
    0.07
    /json
    0.07
     gö
    0.07
    Activations Density 0.002%

    No Known Activations