© 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. 108768
    Prev
    Next
    INDEX
    Explanations

    then

    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
     выиг
    -0.08
     получается
    -0.08
     implying
    -0.08
    trial
    -0.08
     Cos
    -0.08
     hoeveel
    -0.07
    ή
    -0.07
     결국
    -0.07
     subtraction
    -0.07
    subtract
    -0.07
    POSITIVE LOGITS
    深入
    0.09
    重点
    0.08
    0.08
    针对
    0.08
     substantive
    0.08
    进行
    0.08
    述
    0.08
    वार
    0.07
    णे
    0.07
    分析
    0.07
    Activations Density 0.021%
    No Known Activations