Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 88118
    Prev
    Next
    INDEX
    Explanations

    logic puzzles

    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
    几年
    -0.09
     cruising
    -0.08
     达
    -0.08
     soaring
    -0.08
    超过
    -0.08
     loisirs
    -0.08
    |max
    -0.08
     longues
    -0.08
    完成
    -0.08
    突出
    -0.08
    POSITIVE LOGITS
     liar
    0.12
     Truth
    0.10
     deceit
    0.10
     accusation
    0.10
     truth
    0.09
     truthful
    0.09
     Unknown
    0.09
     undead
    0.09
     accusations
    0.09
     individuals
    0.09
    Activations Density 0.017%

    No Known Activations