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. 49130
    Prev
    Next
    INDEX
    Explanations

    VPN

    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
     coag
    -0.08
     изделий
    -0.08
    uksessa
    -0.08
     equation
    -0.08
     يس
    -0.08
     calculus
    -0.08
    raint
    -0.07
     Ø
    -0.07
     GUIDE
    -0.07
     Sewing
    -0.07
    POSITIVE LOGITS
     VPN
    0.10
    Geo
    0.10
     anonymity
    0.09
    internet
    0.09
     geo
    0.09
    .Geo
    0.09
     anonym
    0.09
     internet
    0.09
    onym
    0.09
    VPN
    0.09
    Activations Density 0.011%

    No Known Activations