© 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. 29559
    Prev
    Next
    INDEX
    Explanations

    math equations

    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
    offer
    -0.07
     следующие
    -0.07
    隐
    -0.07
     عادة
    -0.07
     inm
    -0.07
    െന്ന്
    -0.07
     traz
    -0.07
    进一步
    -0.07
     کیوں
    -0.07
    ряд
    -0.07
    POSITIVE LOGITS
     nth
    0.08
    Nth
    0.08
     WTO
    0.08
     kore
    0.08
     eight
    0.07
     fif
    0.07
    ffset
    0.07
     sixteen
    0.07
    nth
    0.07
     Spare
    0.07
    Activations Density 0.013%

    No Known Activations