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. 55069
    Prev
    Next
    INDEX
    Explanations

    Nuclear reactions

    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
     minimized
    -0.08
     toothpaste
    -0.08
    Berry
    -0.08
    Field
    -0.08
    _PANEL
    -0.07
     junta
    -0.07
     corrupted
    -0.07
     dva
    -0.07
     homenagem
    -0.07
     vine
    -0.07
    POSITIVE LOGITS
     neutron
    0.11
     auprès
    0.09
    utron
    0.09
    .stdin
    0.09
     Spielen
    0.09
    اذا
    0.08
     astroph
    0.08
    iesel
    0.08
     درخواست
    0.08
    .requests
    0.08
    Activations Density 0.002%

    No Known Activations