© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 99187
    Prev
    Next
    INDEX
    Explanations

    loop

    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
     manifestation
    -0.08
     manifestations
    -0.08
    Burst
    -0.08
    -0.07
     manifestação
    -0.07
     markers
    -0.07
    located
    -0.07
     located
    -0.07
    િયમ
    -0.07
     breakpoint
    -0.07
    POSITIVE LOGITS
     recycle
    0.14
     recycling
    0.13
     recicl
    0.12
     recic
    0.11
     recycled
    0.11
    循环
    0.10
     Recycling
    0.10
    .recycle
    0.10
    .dispose
    0.10
     wastewater
    0.10
    Activations Density 0.009%

    No Known Activations