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

    Neuronpedia

    APICircuit 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. 60769
    Prev
    Next
    INDEX
    Explanations

    loaded questions

    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
     Mun
    -0.08
     શકાય
    -0.08
    Mun
    -0.08
    graduate
    -0.08
    uatan
    -0.08
     yhd
    -0.08
     бли
    -0.08
     Empower
    -0.07
     piir
    -0.07
     મેળવ
    -0.07
    POSITIVE LOGITS
     implicitly
    0.13
     implicit
    0.12
    Implicit
    0.11
    implicit
    0.11
    implicitly
    0.10
     underlying
    0.09
     inherent
    0.09
     préalable
    0.08
     activation
    0.08
     wagers
    0.08
    Activations Density 0.007%

    No Known Activations