Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 46983
    Prev
    Next
    INDEX
    Explanations

    the

    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
     aval
    -0.08
    -0.08
    لت
    -0.08
    لز
    -0.08
    293
    -0.08
     synchronize
    -0.08
    ಕರು
    -0.07
     الاح
    -0.07
    956
    -0.07
    عاون
    -0.07
    POSITIVE LOGITS
     counter
    0.08
     situation
    0.08
     incarnation
    0.08
     Kim
    0.08
     regime
    0.07
     commiss
    0.07
     Ruf
    0.07
     vět
    0.07
     IPV
    0.07
     pac
    0.07
    Activations Density 0.800%

    No Known Activations