Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 75334
    Prev
    Next
    INDEX
    Explanations

    pre-tax

    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
    ایت
    -0.08
    ाफी
    -0.08
     valt
    -0.07
    erst
    -0.07
    Solver
    -0.07
     Fib
    -0.07
    өп
    -0.07
     replication
    -0.07
     filed
    -0.07
     clim
    -0.07
    POSITIVE LOGITS
    ’une
    0.08
     создания
    0.08
     twor
    0.08
     cria
    0.08
    ’un
    0.08
     infrastructure
    0.07
     jack
    0.07
     sucre
    0.07
     axes
    0.07
    -btn
    0.07
    Activations Density 0.002%

    No Known Activations