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. 3-RESID-POST-AA
    6. 1797
    Prev
    Next
    INDEX
    Explanations

    Schwartz

    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
    -0.08
     stumble
    -0.07
     stre
    -0.07
    .CLIENT
    -0.07
    黃
    -0.07
     يب
    -0.07
     crow
    -0.07
    ARR
    -0.07
     arr
    -0.07
    Dyn
    -0.07
    POSITIVE LOGITS
    บาล
    0.07
    ма
    0.07
    ima
    0.07
    crimin
    0.07
     Delphi
    0.07
     Connecting
    0.07
    .Resize
    0.07
     Resize
    0.07
     Patio
    0.07
     Balt
    0.07
    Activations Density 0.001%

    No Known Activations