© 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. 7-RESID-POST-AA
    11. 1326
    Prev
    Next
    INDEX
    Explanations

    sleek

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     meis
    -0.09
     scap
    -0.09
     kindness
    -0.08
     mirac
    -0.08
     milag
    -0.07
    272
    -0.07
     गाय
    -0.07
     bride
    -0.07
     Relief
    -0.07
     alleviate
    -0.07
    POSITIVE LOGITS
    Saver
    0.08
    저
    0.08
     veins
    0.07
    ty
    0.07
    科技
    0.07
    柏
    0.07
     showroom
    0.07
    研发
    0.07
    Ti
    0.07
     در
    0.07
    Activations Density 0.003%

    No Known Activations