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. 119360
    Prev
    Next
    INDEX
    Explanations

    Command line commands

    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
    ků
    -0.07
    ups
    -0.07
     steeds
    -0.07
    र्ड
    -0.07
    assembl
    -0.07
     folks
    -0.07
    skem
    -0.07
    kách
    -0.07
    andang
    -0.07
    HONE
    -0.07
    POSITIVE LOGITS
     골
    0.09
     fournit
    0.08
    .bad
    0.08
     Mr
    0.08
     boa
    0.08
     yeast
    0.08
     schlecht
    0.08
     anore
    0.08
     ọnụ
    0.08
     появ
    0.07
    Activations Density 0.002%

    No Known Activations