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. 53049
    Prev
    Next
    INDEX
    Explanations

    spending

    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
     Panc
    -0.09
     stigma
    -0.08
    ysters
    -0.08
     stig
    -0.08
     Multi
    -0.08
     blobs
    -0.07
    abilis
    -0.07
     buzz
    -0.07
     Voraussetzungen
    -0.07
     dices
    -0.07
    POSITIVE LOGITS
    -ho
    0.08
    량
    0.08
     대비
    0.08
    Ho
    0.08
    -orang
    0.08
     surplus
    0.08
    사항
    0.08
     coups
    0.07
    수가
    0.07
     Ho
    0.07
    Activations Density 0.010%

    No Known Activations