© 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. 30082
    Prev
    Next
    INDEX
    Explanations

    foam

    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
    urwa
    -0.08
    әм
    -0.08
    重大
    -0.07
    Permit
    -0.07
     себя
    -0.07
     mochila
    -0.07
     desmont
    -0.07
    !="
    -0.07
    казыва
    -0.07
    License
    -0.07
    POSITIVE LOGITS
     foam
    0.09
     mousse
    0.08
    �
    0.08
     gums
    0.08
    顶部
    0.08
     discussie
    0.08
    adam
    0.08
     biodegradable
    0.08
     sensations
    0.08
     oats
    0.07
    Activations Density 0.004%

    No Known Activations