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. 106072
    Prev
    Next
    INDEX
    Explanations

    computer code

    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
     filtration
    -0.08
     filtr
    -0.08
     sensory
    -0.08
     oppressed
    -0.08
     billing
    -0.08
    筛
    -0.08
     ammonia
    -0.08
     food
    -0.07
     prisma
    -0.07
     flotation
    -0.07
    POSITIVE LOGITS
     Jump
    0.11
    Jump
    0.11
    jump
    0.11
    jmp
    0.11
    _jump
    0.10
     jumps
    0.10
     jump
    0.10
    ジャン
    0.10
    .redirect
    0.10
    .jump
    0.10
    Activations Density 0.003%

    No Known Activations