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. 49368
    Prev
    Next
    INDEX
    Explanations

    period

    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
    Trading
    -0.08
    /div
    -0.08
     центра
    -0.08
    .Forms
    -0.08
    ENDED
    -0.07
     tratando
    -0.07
    БО
    -0.07
    ERING
    -0.07
    VERSION
    -0.07
     hierarchy
    -0.07
    POSITIVE LOGITS
    375
    0.10
    550
    0.09
    627
    0.09
    370
    0.08
    .iloc
    0.08
    526
    0.08
    531
    0.08
     samu
    0.08
    534
    0.08
    501
    0.08
    Activations Density 0.028%

    No Known Activations