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. 45056
    Prev
    Next
    INDEX
    Explanations

    wastewater treatment

    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
     illusion
    -0.08
     circles
    -0.08
    (minutes
    -0.08
     rumor
    -0.08
     podstaw
    -0.07
     voeg
    -0.07
     solidity
    -0.07
     milag
    -0.07
     sluč
    -0.07
     disaster
    -0.07
    POSITIVE LOGITS
    rang
    0.08
     сме
    0.08
     recoger
    0.08
     recoge
    0.08
     Sang
    0.08
     уй
    0.08
    tings
    0.08
    amble
    0.08
     طن
    0.08
     produzido
    0.08
    Activations Density 0.004%

    No Known Activations