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. 45176
    Prev
    Next
    INDEX
    Explanations

    1

    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
    ingly
    -0.09
    सा
    -0.07
     тих
    -0.07
    awasan
    -0.07
    ’:
    -0.07
     united
    -0.07
     따
    -0.07
     आयोजित
    -0.07
     credito
    -0.07
     jointly
    -0.07
    POSITIVE LOGITS
     gord
    0.08
     moz
    0.08
     höch
    0.08
     Conway
    0.08
     неод
    0.08
     Cout
    0.08
    moz
    0.08
     מופ
    0.08
     monarch
    0.07
    arit
    0.07
    Activations Density 0.005%

    No Known Activations