© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 44899
    Prev
    Next
    INDEX
    Explanations

    geometrical labeling of vertices

    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
    Age
    -0.08
    ിദ
    -0.07
    regex
    -0.07
    Histogram
    -0.07
    uli
    -0.07
    .Normalize
    -0.07
    stoi
    -0.07
     brutally
    -0.07
    osest
    -0.07
    (age
    -0.07
    POSITIVE LOGITS
     clockwise
    0.10
     numbering
    0.10
     الرب
    0.10
     lettering
    0.10
     ordered
    0.09
     numbered
    0.09
     sequential
    0.09
     consecut
    0.08
    四色
    0.08
    连续
    0.08
    Activations Density 0.056%

    No Known Activations