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. 44138
    Prev
    Next
    INDEX
    Explanations

    Quotation marks

    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
     feitas
    -0.08
     FMC
    -0.08
     ше
    -0.08
     rid
    -0.07
     parag
    -0.07
    �
    -0.07
    PSD
    -0.07
    Hoc
    -0.07
     hinge
    -0.07
     Hoc
    -0.07
    POSITIVE LOGITS
    ၊
    0.08
     объ
    0.08
     হলো
    0.08
     배
    0.08
    04
    0.08
     đỏ
    0.08
    ://${
    0.07
     Legacy
    0.07
    τας
    0.07
     wh
    0.07
    Activations Density 0.124%

    No Known Activations