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. 29825
    Prev
    Next
    INDEX
    Explanations

    data processing/numbers

    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
    appointments
    -0.09
     announcing
    -0.09
    Countdown
    -0.08
     funding
    -0.08
    Advertising
    -0.08
    _tracker
    -0.08
    Funding
    -0.08
    ্যম
    -0.08
    _draw
    -0.08
     appointments
    -0.07
    POSITIVE LOGITS
     preprocessing
    0.16
     preprocess
    0.14
     преобраз
    0.12
    .Normalize
    0.12
    .normalize
    0.12
     transformations
    0.12
    .convert
    0.12
     homogen
    0.12
     flatten
    0.12
     removing
    0.11
    Activations Density 0.046%

    No Known Activations