© 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. 3-RESID-POST-AA
    11. 12717
    Prev
    Next
    INDEX
    Explanations

    enough

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     корз
    -0.08
     Ax
    -0.08
     месте
    -0.08
     Narc
    -0.08
     рабоч
    -0.08
    punk
    -0.08
     слишком
    -0.07
    lir
    -0.07
     thérape
    -0.07
     cannabinoids
    -0.07
    POSITIVE LOGITS
     Cole
    0.08
     bun
    0.07
    Berlin
    0.07
    旗
    0.07
     Berlin
    0.07
     shiga
    0.07
     bal
    0.07
     megs
    0.07
     arrivals
    0.07
     પોતાની
    0.07
    Activations Density 0.004%

    No Known Activations