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. 129878
    Prev
    Next
    INDEX
    Explanations

    code

    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
     hängt
    -0.08
    スタ
    -0.08
     dut
    -0.07
     Kom
    -0.07
     stem
    -0.07
    Буд
    -0.07
     depend
    -0.07
     solange
    -0.07
     instability
    -0.07
    Д
    -0.06
    POSITIVE LOGITS
    lezza
    0.09
    icity
    0.09
    icatie
    0.09
     Heathrow
    0.09
    icc
    0.08
    icin
    0.08
    zinha
    0.08
    icated
    0.08
    ದ್ದು
    0.08
    ෙන්
    0.08
    Activations Density 0.001%

    No Known Activations