© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 64923
    Prev
    Next
    INDEX
    Explanations

    plants

    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
     مي
    -0.07
     excite
    -0.07
     flag
    -0.07
    lywood
    -0.07
     libres
    -0.07
    辖
    -0.07
    rs
    -0.07
    flag
    -0.06
    CD
    -0.06
    mages
    -0.06
    POSITIVE LOGITS
     Kada
    0.08
    Dl
    0.08
    Ql
    0.08
    کل
    0.08
     produces
    0.08
     Dina
    0.08
    -produced
    0.08
     дана
    0.08
    bitcoin
    0.08
     przeb
    0.08
    Activations Density 0.016%

    No Known Activations