© 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. 3-RESID-POST-AA
    11. 2640
    Prev
    Next
    INDEX
    Explanations

    digital

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     grap
    -0.08
     люб
    -0.08
    式
    -0.08
    Ster
    -0.08
     �
    -0.08
     sand
    -0.08
    rd
    -0.08
    ership
    -0.08
     ster
    -0.08
    pier
    -0.07
    POSITIVE LOGITS
     Nicola
    0.08
     �
    0.08
     tos
    0.08
    倾
    0.07
    �
    0.07
     Neal
    0.07
    投入
    0.07
    آ
    0.07
    纠
    0.07
    把
    0.07
    Activations Density 0.018%

    No Known Activations