© 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. 65311
    Prev
    Next
    INDEX
    Explanations

    join

    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
    ikov
    -0.09
     Torch
    -0.08
     diverted
    -0.08
     Club
    -0.08
     yetiş
    -0.08
     hábitos
    -0.07
    yan
    -0.07
     инициатив
    -0.07
     призн
    -0.07
     přij
    -0.07
    POSITIVE LOGITS
     merges
    0.09
     JOIN
    0.09
     merge
    0.08
     연결
    0.08
     الرب
    0.08
     જોડ
    0.08
     cyl
    0.08
    JOIN
    0.08
     بينها
    0.08
    กัน
    0.08
    Activations Density 0.007%

    No Known Activations