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. 112810
    Prev
    Next
    INDEX
    Explanations

    direct

    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
     Wagen
    -0.08
    opin
    -0.08
     vertreten
    -0.08
     Kamin
    -0.08
    venz
    -0.08
     Lords
    -0.08
     Endless
    -0.08
     Crock
    -0.08
     Organic
    -0.08
    cken
    -0.08
    POSITIVE LOGITS
     calculations
    0.09
     concret
    0.08
     расч
    0.08
     tedious
    0.08
     calculation
    0.08
    計
    0.08
     characteristic
    0.08
     계산
    0.08
     formulas
    0.08
     calculates
    0.08
    Activations Density 0.010%

    No Known Activations