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. 65784
    Prev
    Next
    INDEX
    Explanations

    ha

    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
    uet
    -0.08
     Familien
    -0.07
    family
    -0.07
    Family
    -0.07
    ardin
    -0.07
     family
    -0.07
    adoop
    -0.07
    uming
    -0.07
     Family
    -0.07
    ul
    -0.07
    POSITIVE LOGITS
     covid
    0.08
     CLASS
    0.08
     Classified
    0.08
    NOV
    0.08
    突
    0.08
    classified
    0.08
    十四
    0.07
     inició
    0.07
     pathogens
    0.07
     potr
    0.07
    Activations Density 0.001%

    No Known Activations