© 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. 47964
    Prev
    Next
    INDEX
    Explanations

    start

    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
    ুশ
    -0.08
     pain
    -0.07
    inen
    -0.07
     THC
    -0.07
    着
    -0.07
     ആശ
    -0.07
     Fey
    -0.07
     нос
    -0.07
    涉
    -0.07
    urable
    -0.07
    POSITIVE LOGITS
    Seconds
    0.09
     Amount
    0.08
     seconds
    0.08
    Oo
    0.08
     برابر
    0.08
     beweging
    0.08
     ಪಡೆಯ
    0.08
     eterna
    0.07
     역사
    0.07
     taki
    0.07
    Activations Density 0.002%

    No Known Activations