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. 9252
    Prev
    Next
    INDEX
    Explanations

    avoiding taking a stance

    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
     tallest
    -0.09
     format
    -0.09
     формат
    -0.08
    .format
    -0.08
    Format
    -0.08
    format
    -0.08
     monitor
    -0.08
     metric
    -0.08
    -format
    -0.07
     adobe
    -0.07
    POSITIVE LOGITS
     opinions
    0.14
    观点
    0.13
     stance
    0.13
     opiniones
    0.12
     Opinions
    0.12
    意见
    0.12
     opinion
    0.11
     outspoken
    0.11
     opiniões
    0.11
     의견
    0.11
    Activations Density 0.058%

    No Known Activations