© 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. 24640
    Prev
    Next
    INDEX
    Explanations

    code

    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
     testimonials
    -0.08
    튀
    -0.08
     recommendations
    -0.08
     lema
    -0.08
    _ads
    -0.08
     incorporated
    -0.08
    glas
    -0.07
     Incorporated
    -0.07
    举报
    -0.07
    ligation
    -0.07
    POSITIVE LOGITS
     ASCII
    0.08
     Nikol
    0.08
    ASCII
    0.08
     rango
    0.08
     диапаз
    0.08
     нерв
    0.08
     BETWEEN
    0.08
     clavier
    0.08
     alphabetical
    0.08
     /*
    0.07
    Activations Density 0.005%

    No Known Activations