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. 30804
    Prev
    Next
    INDEX
    Explanations

    one

    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
    lerden
    -0.08
    MEM
    -0.08
    ælde
    -0.08
    _than
    -0.08
     MEM
    -0.07
     insanların
    -0.07
     Keynes
    -0.07
     memories
    -0.07
     freeing
    -0.07
     tener
    -0.07
    POSITIVE LOGITS
     uppercase
    0.09
    ுத்த
    0.08
     atento
    0.08
     lú
    0.08
    дый
    0.07
    ínu
    0.07
     кла
    0.07
     ক্ল
    0.07
     Athlete
    0.07
     Translation
    0.07
    Activations Density 0.009%

    No Known Activations