© 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
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 91278
    Prev
    Next
    INDEX
    Explanations

    beginnings and transitions

    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
     genes
    -0.08
    őség
    -0.08
    арон
    -0.07
    드
    -0.07
     gene
    -0.07
    \<
    -0.07
     prefix
    -0.07
    .ITEM
    -0.07
     Gene
    -0.07
    refix
    -0.07
    POSITIVE LOGITS
     sabendo
    0.09
     থেকেই
    0.09
     limpa
    0.09
     limpio
    0.09
     நிலைய
    0.09
     अवस्था
    0.09
     weinig
    0.09
     unmet
    0.08
     stanje
    0.08
     teadm
    0.08
    Activations Density 0.105%

    No Known Activations