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. 44973
    Prev
    Next
    INDEX
    Explanations

    cumulative

    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
     awkward
    -0.08
     afl
    -0.08
    jama
    -0.08
    -peer
    -0.08
    оком
    -0.08
     agon
    -0.07
    Miss
    -0.07
    Brook
    -0.07
    {k
    -0.07
    (java
    -0.07
    POSITIVE LOGITS
     cumulative
    0.12
     consecutive
    0.11
     cum
    0.10
     exceed
    0.09
    累计
    0.09
     exceeds
    0.09
     consecut
    0.09
     cumul
    0.08
    umulative
    0.08
     accumulated
    0.08
    Activations Density 0.018%

    No Known Activations