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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 9039
    Prev
    Next
    INDEX
    Explanations

    th

    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
    屯
    -0.08
     codice
    -0.08
     farmland
    -0.08
     Jacobs
    -0.08
     bont
    -0.08
    .foundation
    -0.08
    东北
    -0.08
     fand
    -0.07
     buon
    -0.07
    赌博
    -0.07
    POSITIVE LOGITS
     carrière
    0.10
     prestigious
    0.09
     ascent
    0.09
     progression
    0.09
     ambitions
    0.09
     asc
    0.09
    _relation
    0.09
     ascend
    0.09
     career
    0.09
     careers
    0.08
    Activations Density 0.006%

    No Known Activations