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. 60518
    Prev
    Next
    INDEX
    Explanations

    numbers, math

    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
     grading
    -0.08
    zn
    -0.08
    endum
    -0.07
     Cartier
    -0.07
    fully
    -0.07
    gn
    -0.07
    丽
    -0.07
    abcd
    -0.07
     skil
    -0.07
     ż
    -0.07
    POSITIVE LOGITS
    rd
    0.08
    (三
    0.08
    Turbo
    0.07
    ()\
    0.07
    scratch
    0.07
    削
    0.07
     DEG
    0.07
     techno
    0.07
    ême
    0.07
     pocket
    0.07
    Activations Density 0.092%

    No Known Activations