© 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. 94929
    Prev
    Next
    INDEX
    Explanations

    oasis

    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
    اد
    -0.08
    (actor
    -0.07
    Diameter
    -0.07
    actor
    -0.07
     উৎপ
    -0.07
    #define
    -0.07
     পড়
    -0.07
     sanction
    -0.07
     erect
    -0.07
    Relation
    -0.07
    POSITIVE LOGITS
     oasis
    0.09
     tranquille
    0.09
     refuge
    0.09
     niches
    0.08
     tranqu
    0.08
     Tai
    0.08
    �
    0.07
     tranquill
    0.07
     tranquila
    0.07
     haven
    0.07
    Activations Density 0.014%

    No Known Activations