© 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. 12931
    Prev
    Next
    INDEX
    Explanations

    ว

    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
    Fac
    -0.08
     verbal
    -0.08
    ublado
    -0.07
    रीन
    -0.07
     fleece
    -0.07
     reneg
    -0.07
     Brook
    -0.07
     mates
    -0.07
     Swim
    -0.07
    qn
    -0.07
    POSITIVE LOGITS
     Ray
    0.07
     acute
    0.07
     письмо
    0.07
     Yo
    0.07
     ray
    0.07
     представ
    0.07
     ввод
    0.07
     рекоменду
    0.07
    ­l
    0.07
     влад
    0.07
    Activations Density 0.000%

    No Known Activations