© 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. 162
    Prev
    Next
    INDEX
    Explanations

    content

    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
    heits
    -0.10
    Shrink
    -0.08
    למיד
    -0.08
     inflated
    -0.08
    Infl
    -0.08
    ned
    -0.08
    heids
    -0.08
    Sar
    -0.07
     Leadpages
    -0.07
     sabot
    -0.07
    POSITIVE LOGITS
     Govern
    0.08
     Movies
    0.08
    _movies
    0.08
     roman
    0.08
     calme
    0.07
     Copp
    0.07
     SPO
    0.07
     lenta
    0.07
    /videos
    0.07
     cinemat
    0.07
    Activations Density 0.007%

    No Known Activations