© 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. 2731
    Prev
    Next
    INDEX
    Explanations

    front

    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
     monarch
    -0.08
     Marina
    -0.08
     Kai
    -0.08
     volta
    -0.07
     profunda
    -0.07
     Musa
    -0.07
    ള്ള
    -0.07
     conspir
    -0.07
     es
    -0.07
     Qa
    -0.07
    POSITIVE LOGITS
    #print
    0.08
    ವಹ
    0.07
     county
    0.07
    Void
    0.07
    安县
    0.07
    Dias
    0.07
     /^\
    0.07
    Accumulator
    0.07
    写真
    0.07
     hitters
    0.07
    Activations Density 0.009%

    No Known Activations