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. 60509
    Prev
    Next
    INDEX
    Explanations

    what people think of

    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
    dule
    -0.08
    Advantages
    -0.08
    ải
    -0.08
     выдерж
    -0.08
     Advantages
    -0.08
     Ignite
    -0.08
    Earn
    -0.08
    Benefit
    -0.07
     kjærl
    -0.07
    Certificates
    -0.07
    POSITIVE LOGITS
     iconic
    0.12
     synonymous
    0.11
     stereotyp
    0.11
     popularly
    0.10
     recognizable
    0.09
     prominent
    0.09
     stereotypes
    0.09
     preconce
    0.09
    代表
    0.09
     대표
    0.09
    Activations Density 0.085%

    No Known Activations