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. 55124
    Prev
    Next
    INDEX
    Explanations

    stripe

    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
     numbering
    -0.08
     counted
    -0.07
     الأسعار
    -0.07
     Kalam
    -0.07
     sponsor
    -0.07
     siv
    -0.07
    建
    -0.07
     цены
    -0.07
     pairing
    -0.07
     tuy
    -0.07
    POSITIVE LOGITS
    Logout
    0.09
    habil
    0.08
    खे
    0.08
     sacar
    0.08
    -human
    0.08
    vient
    0.08
     जात
    0.08
     खे
    0.08
     WCHAR
    0.08
     zumindest
    0.08
    Activations Density 0.002%

    No Known Activations