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. 43651
    Prev
    Next
    INDEX
    Explanations

    tumor

    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
     heartfelt
    -0.08
     skepticism
    -0.08
    uvi
    -0.08
     transmission
    -0.07
     contracted
    -0.07
    $temp
    -0.07
     hesitant
    -0.07
    .deepcopy
    -0.07
     chilled
    -0.07
    ská
    -0.07
    POSITIVE LOGITS
     malign
    0.10
     invading
    0.10
     tumors
    0.09
     occupying
    0.08
    occup
    0.08
     опух
    0.08
     الأور
    0.08
    出售
    0.08
    फ
    0.08
     Gothic
    0.08
    Activations Density 0.006%

    No Known Activations