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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 75985
    Prev
    Next
    INDEX
    Explanations

    Code replacement/database config

    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
     Mea
    -0.08
    estimated
    -0.08
    好运
    -0.08
    Modify
    -0.07
    Cons
    -0.07
    adenas
    -0.07
     distribución
    -0.07
    Immutable
    -0.07
    ayon
    -0.07
    leans
    -0.07
    POSITIVE LOGITS
     klaus
    0.08
     ]]
    0.08
    :id
    0.08
    -content
    0.08
    ]][
    0.08
    :name
    0.08
     junge
    0.08
     sql
    0.07
     rechts
    0.07
     rebound
    0.07
    Activations Density 0.000%

    No Known Activations