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. 12161
    Prev
    Next
    INDEX
    Explanations

    Cholera

    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
     competing
    -0.09
    ledu
    -0.08
    成长
    -0.08
     Busy
    -0.08
     хугаца
    -0.07
     wach
    -0.07
     NDA
    -0.07
    hileng
    -0.07
     Lag
    -0.07
    хөөр
    -0.07
    POSITIVE LOGITS
     fever
    0.09
    stede
    0.08
     pepper
    0.08
     Fever
    0.08
     flames
    0.07
     boiling
    0.07
    DEN
    0.07
     ecstatic
    0.07
    amanzi
    0.07
     pts
    0.07
    Activations Density 0.002%

    No Known Activations