Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 53284
    Prev
    Next
    INDEX
    Explanations

    Russian

    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
    .monitor
    -0.08
     ocorre
    -0.08
    encoder
    -0.07
     PEN
    -0.07
     IEC
    -0.07
    .pen
    -0.07
     phil
    -0.07
     ETC
    -0.07
     acontece
    -0.07
     monitored
    -0.07
    POSITIVE LOGITS
    шись
    0.10
    不少
    0.09
     ques
    0.07
    _pic
    0.07
    cow
    0.07
     glimpse
    0.07
    ಡೆ
    0.07
     freezes
    0.07
    财富
    0.07
    DSM
    0.07
    Activations Density 0.068%

    No Known Activations