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. 76516
    Prev
    Next
    INDEX
    Explanations

    prisons and legal issues

    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
     Canva
    -0.09
     customer
    -0.08
     bundles
    -0.07
    ی
    -0.07
    uffix
    -0.07
     detecting
    -0.07
     sweetness
    -0.07
    Brightness
    -0.07
     விவ
    -0.07
     derivatives
    -0.07
    POSITIVE LOGITS
     punitive
    0.13
     prison
    0.13
     detaine
    0.12
     deport
    0.12
     prisoner
    0.12
     incarcer
    0.12
     prisoners
    0.11
     prisons
    0.11
     cárcel
    0.11
     martyr
    0.11
    Activations Density 0.092%

    No Known Activations