© 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. 78420
    Prev
    Next
    INDEX
    Explanations

    periods

    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
    ોચ
    -0.08
     Chad
    -0.08
     sellele
    -0.08
    准
    -0.08
     swim
    -0.08
     잡
    -0.07
     yog
    -0.07
     loy
    -0.07
     Claus
    -0.07
     caça
    -0.07
    POSITIVE LOGITS
    These
    0.09
    러한
    0.08
     Доп
    0.08
    Additionally
    0.08
    According
    0.08
    Govern
    0.08
    Ren
    0.07
    Creating
    0.07
     These
    0.07
    When
    0.07
    Activations Density 0.091%

    No Known Activations