© 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. 23-RESID-POST-AA
    11. 97221
    Prev
    Next
    INDEX
    Explanations

    background details

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Điều
    -0.08
     Ch
    -0.08
     hiểu
    -0.08
     From
    -0.08
     hình
    -0.08
    _vote
    -0.07
     Armstrong
    -0.07
     Ý
    -0.07
     Heritage
    -0.07
     With
    -0.07
    POSITIVE LOGITS
    ENE
    0.09
    Kai
    0.08
    estaan
    0.08
    malar
    0.08
     producent
    0.08
    Exc
    0.07
    ако
    0.07
     malo
    0.07
     ニ
    0.07
     terus
    0.07
    Activations Density 0.001%

    No Known Activations